fix(skills): update datadog-labs/agent-skills to 66c3d94, fix path moves by JAORMX · Pull Request #738 · stacklok/dockyard

JAORMX · 2026-07-03T10:35:23Z

Summary

Supersedes chore(deps): update datadog-labs/agent-skills digest to 66c3d94 #675. Carries the same digest/version bump renovate proposed for all 9 datadog skills, plus path fixes for the 4 that broke.
All 4 dd-llmo-* skills: upstream renamed dd-llmo/llm-obs-* to agent-observability/agent-observability-* at the new ref. Fixed spec.path on each:
- dd-llmo-eval-bootstrap -> agent-observability/agent-observability-eval-bootstrap
- dd-llmo-eval-session-classify -> agent-observability/agent-observability-session-classify
- dd-llmo-eval-trace-rca -> agent-observability/agent-observability-trace-rca
- dd-llmo-experiment-analyzer -> agent-observability/agent-observability-experiment-analyzer
No security findings on any of these 4 once the path resolves.

Test plan

Built dockhand locally, ran validate-skill against all 4 changed spec.yaml files — all Status: VALID
CI green on this PR
Close chore(deps): update datadog-labs/agent-skills digest to 66c3d94 #675 once this merges

Co-Authored-By: Claude Sonnet 5 noreply@anthropic.com

…strap,dd-llmo-eval-session-classify,dd-llmo-eval-trace-rca,dd-llmo-experiment-analyzer,dd-logs,dd-monitors,dd-pup

datadog-labs/agent-skills renamed dd-llmo/llm-obs-* to agent-observability/agent-observability-* at commit 66c3d944, breaking validate-skills and skill-security-scan (checkout failure) for all 4 skills in PR #675. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

toolhive-release-app · 2026-07-03T10:41:21Z

🛡️ Skill Security Scan Results

✅ dd-apm

Status: Passed
Findings: 7
Allowed (not blocking): 3
- COMPOUND_EXTRACT_EXECUTE (Allowed: FP: cisco-ai-skill-scanner matched the documented pup CLI install
  snippet in k8s-ssi/agent-install/SKILL.md:67,
  k8s-ssi/troubleshoot-ssi/SKILL.md:48 and
  linux-ssi/troubleshoot-ssi/SKILL.md:48. The snippet downloads the
  official pup release tarball from the same vendor
  (github.com/datadog-labs/pup/releases, version pinned via the GitHub
  releases API) and pipes it through tar xz into /usr/local/bin — the
  canonical, vendor-published CLI install instruction shown to the user,
  not a hidden/malicious archive payload. No executable threat.
  datadog-labs/agent-skills @9bcb3ceafacae78dbba76c9459a878fc7d6a0d10.
  )
- COMPOUND_EXTRACT_EXECUTE (Allowed: FP: cisco-ai-skill-scanner matched the documented pup CLI install
  snippet in k8s-ssi/agent-install/SKILL.md:67,
  k8s-ssi/troubleshoot-ssi/SKILL.md:48 and
  linux-ssi/troubleshoot-ssi/SKILL.md:48. The snippet downloads the
  official pup release tarball from the same vendor
  (github.com/datadog-labs/pup/releases, version pinned via the GitHub
  releases API) and pipes it through tar xz into /usr/local/bin — the
  canonical, vendor-published CLI install instruction shown to the user,
  not a hidden/malicious archive payload. No executable threat.
  datadog-labs/agent-skills @9bcb3ceafacae78dbba76c9459a878fc7d6a0d10.
  )
- COMPOUND_EXTRACT_EXECUTE (Allowed: FP: cisco-ai-skill-scanner matched the documented pup CLI install
  snippet in k8s-ssi/agent-install/SKILL.md:67,
  k8s-ssi/troubleshoot-ssi/SKILL.md:48 and
  linux-ssi/troubleshoot-ssi/SKILL.md:48. The snippet downloads the
  official pup release tarball from the same vendor
  (github.com/datadog-labs/pup/releases, version pinned via the GitHub
  releases API) and pipes it through tar xz into /usr/local/bin — the
  canonical, vendor-published CLI install instruction shown to the user,
  not a hidden/malicious archive payload. No executable threat.
  datadog-labs/agent-skills @9bcb3ceafacae78dbba76c9459a878fc7d6a0d10.
  )

✅ dd-docs

Status: Passed
Findings: 4
Allowed (not blocking): 1
- MANIFEST_MISSING_LICENSE (Allowed: datadog-labs/agent-skills is licensed MIT at the repository root; upstream does not embed an SPDX license identifier in per-skill SKILL.md frontmatter.)

❌ dd-llmo-eval-bootstrap

Status: Failed
Findings: 484
Blocking: 6

Blocking issues:

[LLM_SKILL_DISCOVERY_ABUSE] (HIGH) The skill description contains an unusually large number of activation trigger phrases: 'bootstrap evaluators', 'generate evaluators', 'create evals from traces', 'eval bootstrap', 'write evaluators', 'build eval suite', 'publish evaluators', as well as technical terms like 'BaseEvaluator/LLMJudge code' and 'online judge configs'. This broad keyword baiting increases the likelihood of unintended activation when users discuss evaluation topics generally, potentially causing the skill to interact with production Datadog environments and create resources without explicit user intent. (SKILL.md)
[PG_PII_SSN_HARVESTING] (CRITICAL) Pattern detected: prompt template, parsin (SKILL.md:70)
[ATR_2026_00020] (HIGH) Pattern detected: system_prompt= (SKILL.md:161)
[ATR_2026_00062] (CRITICAL) Pattern detected: init (SKILL.md:245)
[ATR_2026_00062] (CRITICAL) Pattern detected: init (SKILL.md:246)
[ATR_2026_00063] (CRITICAL) Pattern detected: compress (SKILL.md:365)

Allowlisted (not blocking):

MANIFEST_MISSING_LICENSE (Allowed: datadog-labs/agent-skills is licensed MIT at the repository root; upstream does not embed an SPDX license identifier in per-skill SKILL.md frontmatter.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00040 (Allowed: FP: matched the word 'Deploy' in prose 'Deploy to Datadog LLM Experiments' (SKILL.md:729). Documentation step, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00040 (Allowed: FP: matched the word 'Deploy' in prose 'Deploy to Datadog LLM Experiments' (SKILL.md:729). Documentation step, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00040 (Allowed: FP: matched the word 'Deploy' in prose 'Deploy to Datadog LLM Experiments' (SKILL.md:729). Documentation step, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00040 (Allowed: FP: matched the word 'Deploy' in prose 'Deploy to Datadog LLM Experiments' (SKILL.md:729). Documentation step, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00213 (Allowed: FP: matched the literal words 'system prompt' / 'System Prompt' in prose describing Datadog span fields and eval dimensions. Documentation, not a system-prompt-extraction attack. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00213 (Allowed: FP: matched the literal words 'system prompt' / 'System Prompt' in prose describing Datadog span fields and eval dimensions. Documentation, not a system-prompt-extraction attack. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00051 (Allowed: FP: matched the prose phrase 'For each' (loop-over-traces guidance). Documentation, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00213 (Allowed: FP: matched the literal words 'system prompt' / 'System Prompt' in prose describing Datadog span fields and eval dimensions. Documentation, not a system-prompt-extraction attack. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00213 (Allowed: FP: matched the literal words 'system prompt' / 'System Prompt' in prose describing Datadog span fields and eval dimensions. Documentation, not a system-prompt-extraction attack. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00001 (Allowed: FP: matched prose 'these become the domain-specific evaluator category' (SKILL.md:371). Documentation guidance, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00090 (Allowed: FP: matched prose 'Extract the rules implicitly followed across observed outputs' (SKILL.md:375). Analysis guidance, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00032 (Allowed: FP: matched prose 'skip this step and proceed directly' (SKILL.md:396). Workflow instruction, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00213 (Allowed: FP: matched the literal words 'system prompt' / 'System Prompt' in prose describing Datadog span fields and eval dimensions. Documentation, not a system-prompt-extraction attack. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00110 (Allowed: FP: matched eval ( inside an example Python evaluator function signature. Not a code-eval sink. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00051 (Allowed: FP: matched the prose phrase 'For each' (loop-over-traces guidance). Documentation, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00051 (Allowed: FP: matched the prose phrase 'For each' (loop-over-traces guidance). Documentation, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
PG_EXFIL_MARKDOWN_LINK (Allowed: False positive - the flagged pattern is a markdown link template
[Trace {first_8}...](https://app.datadoghq.com/llm/traces?query=trace_id:{full_32_char_id})
used by the skill to cite trace evidence to the USER. The destination
(app.datadoghq.com) is the user's own Datadog SaaS tenant; the encoded
value is a trace_id surfaced from the user's own LLM Observability data
— not exfiltrated agent context. The link is rendered for the user to
click and verify the cited trace, which is the explicit purpose stated
in the "Show your work" operating rule. Verified at digest
98343f304cbd4439b3d7640cfe64f78070e44d68 (SKILL.md:681).
)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00051 (Allowed: FP: matched the prose phrase 'For each' (loop-over-traces guidance). Documentation, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00213 (Allowed: FP: matched the literal words 'system prompt' / 'System Prompt' in prose describing Datadog span fields and eval dimensions. Documentation, not a system-prompt-extraction attack. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00030 (Allowed: FP: matched run() (SKILL.md:613) inside an example Python experiment-client snippet. Not an attack vector. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00051 (Allowed: FP: matched the prose phrase 'For each' (loop-over-traces guidance). Documentation, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00040 (Allowed: FP: matched the word 'Deploy' in prose 'Deploy to Datadog LLM Experiments' (SKILL.md:729). Documentation step, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00004 (Allowed: FP: matched JSON/code example fragment {role: " in an eval message schema. Documentation/code, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00213 (Allowed: FP: matched the literal words 'system prompt' / 'System Prompt' in prose describing Datadog span fields and eval dimensions. Documentation, not a system-prompt-extraction attack. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00213 (Allowed: FP: matched the literal words 'system prompt' / 'System Prompt' in prose describing Datadog span fields and eval dimensions. Documentation, not a system-prompt-extraction attack. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00091 (Allowed: FP: matched literal \n newline escapes inside JSON/code example blocks. Documentation/code, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00091 (Allowed: FP: matched literal \n newline escapes inside JSON/code example blocks. Documentation/code, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00091 (Allowed: FP: matched literal \n newline escapes inside JSON/code example blocks. Documentation/code, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00091 (Allowed: FP: matched literal \n newline escapes inside JSON/code example blocks. Documentation/code, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00213 (Allowed: FP: matched the literal words 'system prompt' / 'System Prompt' in prose describing Datadog span fields and eval dimensions. Documentation, not a system-prompt-extraction attack. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00091 (Allowed: FP: matched literal \n newline escapes inside JSON/code example blocks. Documentation/code, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00091 (Allowed: FP: matched literal \n newline escapes inside JSON/code example blocks. Documentation/code, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00091 (Allowed: FP: matched literal \n newline escapes inside JSON/code example blocks. Documentation/code, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00091 (Allowed: FP: matched literal \n newline escapes inside JSON/code example blocks. Documentation/code, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00040 (Allowed: FP: matched the word 'Deploy' in prose 'Deploy to Datadog LLM Experiments' (SKILL.md:729). Documentation step, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00051 (Allowed: FP: matched the prose phrase 'For each' (loop-over-traces guidance). Documentation, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00051 (Allowed: FP: matched the prose phrase 'For each' (loop-over-traces guidance). Documentation, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00051 (Allowed: FP: matched the prose phrase 'For each' (loop-over-traces guidance). Documentation, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
PG_EXFIL_MARKDOWN_LINK (Allowed: False positive - the flagged pattern is a markdown link template
[Trace {first_8}...](https://app.datadoghq.com/llm/traces?query=trace_id:{full_32_char_id})
used by the skill to cite trace evidence to the USER. The destination
(app.datadoghq.com) is the user's own Datadog SaaS tenant; the encoded
value is a trace_id surfaced from the user's own LLM Observability data
— not exfiltrated agent context. The link is rendered for the user to
click and verify the cited trace, which is the explicit purpose stated
in the "Show your work" operating rule. Verified at digest
98343f304cbd4439b3d7640cfe64f78070e44d68 (SKILL.md:681).
)
ATR_2026_00111 (Allowed: FP: word-fragment matches — summarizing a policy (example intent category), eval_scope (identifier). Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00066 (Allowed: FP: matched Datadog eval-prompt template placeholders — {{input_data}}, {{output_data}}, {{span_input}}, {{meta.input.messages[*].content}}. These are the documented templating syntax for LLM-judge prompts, not injected payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00010 (Allowed: FP: matched backtick-wrapped upstream tool/CLI names — get_llmobs_evaluator, list_llmobs_eval*, create_or_update_llmobs_eval*, pup llm-obs evals get-eval, /eval. Documentation references to tools the skill instructs the agent to call against the user's own Datadog tenant, not executed payloads. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00012 (Allowed: FP: word-fragment matches — integration_account_id, table cells, tool-name fragments like get_llmobs_span_details(trace_id. Documentation strings, no executable threat. datadog-labs/agent-skills @9bcb3ce.)
ATR_2026_00091 (Allowed: FP: matched literal \n newline escapes inside JSON/code example blocks. Documentation/code, no executable threat. datadog-labs/agent-skills @9bcb3ce.)

✅ dd-llmo-eval-session-classify

Status: Passed
Findings: 3

✅ dd-llmo-eval-trace-rca

Status: Passed
Findings: 4

✅ dd-llmo-experiment-analyzer

Status: Passed
Findings: 4
Allowed (not blocking): 1
- MANIFEST_MISSING_LICENSE (Allowed: datadog-labs/agent-skills is licensed MIT at the repository root; upstream does not embed an SPDX license identifier in per-skill SKILL.md frontmatter.)

✅ dd-logs

Status: Passed
Findings: 2
Allowed (not blocking): 1
- MANIFEST_MISSING_LICENSE (Allowed: datadog-labs/agent-skills is licensed MIT at the repository root; upstream does not embed an SPDX license identifier in per-skill SKILL.md frontmatter.)

✅ dd-monitors

Status: Passed
Findings: 4
Allowed (not blocking): 1
- MANIFEST_MISSING_LICENSE (Allowed: datadog-labs/agent-skills is licensed MIT at the repository root; upstream does not embed an SPDX license identifier in per-skill SKILL.md frontmatter.)

✅ dd-pup

Status: Passed
Findings: 4
Allowed (not blocking): 1
- MANIFEST_MISSING_LICENSE (Allowed: datadog-labs/agent-skills is licensed MIT at the repository root; upstream does not embed an SPDX license identifier in per-skill SKILL.md frontmatter.)

Summary: Scanned 9 skill(s), found 6 blocking issue(s).

⚠️ Action Required: Review the blocking findings. Add a justified entry to the skill's security.allowed_issues[] in its spec.yaml if the finding is a false positive.

renovate Bot and others added 3 commits July 3, 2026 13:33

chore(deps): update datadog-labs/agent-skills digest to 66c3d94

817a184

chore(skills): bump spec.version for dd-apm,dd-docs,dd-llmo-eval-boot…

7878e0d

…strap,dd-llmo-eval-session-classify,dd-llmo-eval-trace-rca,dd-llmo-experiment-analyzer,dd-logs,dd-monitors,dd-pup

samuv approved these changes Jul 3, 2026

View reviewed changes

Merge branch 'main' into fix/datadog-skills-digest

50e795e

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(skills): update datadog-labs/agent-skills to 66c3d94, fix path moves#738

fix(skills): update datadog-labs/agent-skills to 66c3d94, fix path moves#738
JAORMX wants to merge 4 commits into
mainfrom
fix/datadog-skills-digest

JAORMX commented Jul 3, 2026

Uh oh!

toolhive-release-app Bot commented Jul 3, 2026 •

edited

Loading

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Uh oh!

Conversation

JAORMX commented Jul 3, 2026

Summary

Test plan

Uh oh!

toolhive-release-app Bot commented Jul 3, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🛡️ Skill Security Scan Results

✅ dd-apm

✅ dd-docs

❌ dd-llmo-eval-bootstrap

✅ dd-llmo-eval-session-classify

✅ dd-llmo-eval-trace-rca

✅ dd-llmo-experiment-analyzer

✅ dd-logs

✅ dd-monitors

✅ dd-pup

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

toolhive-release-app Bot commented Jul 3, 2026 •

edited

Loading