Add AgentGuard - AI agent supply chain security tool#21
Open
momenbasel wants to merge 1 commit intoguardrailsio:masterfrom
Open
Add AgentGuard - AI agent supply chain security tool#21momenbasel wants to merge 1 commit intoguardrailsio:masterfrom
momenbasel wants to merge 1 commit intoguardrailsio:masterfrom
Conversation
There was a problem hiding this comment.
Pull request overview
Adds AgentGuard to the README’s “Multi tools” list to highlight an agent-layer supply chain security wrapper for package installation commands used by coding agents.
Changes:
- Add a new “Multi tools” README entry for AgentGuard and describe its purpose (typosquatting/malicious/vuln feed checks before installs).
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| - [GuardRails](https://github.com/apps/guardrails) - A GitHub App that gives you instant security feedback in your Pull Requests. | ||
| - [Hubble](https://github.com/hubblestack/hubble) - Hubble is a modular, open-source security compliance framework. | ||
| - [Salus](https://github.com/coinbase/salus) - Multi purpose security scanning tool supporting Ruby, Node, Python and Go. | ||
| - [AgentGuard](https://github.com/momenbasel/AgentGuard) - AI agent supply chain security tool that intercepts package installs from coding agents (Claude Code, Codex, Copilot) and validates against typosquatting, known malicious packages, and live OSV.dev feeds before execution. |
There was a problem hiding this comment.
This list entry’s description is much longer/more detailed than the surrounding “Multi tools” items, which makes the section harder to scan. Consider shortening it to a single concise sentence consistent with the other bullets (e.g., focus on “agent-layer supply-chain validation for pip/npm/cargo installs”).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR adds AgentGuard to the Multi tools section.
AgentGuard is an AI agent supply chain security tool that intercepts package install commands issued by coding agents (Claude Code, Codex, Copilot) and validates them against:
It acts as a transparent wrapper around pip/npm/cargo, blocking dangerous installs before they execute. With LLM-powered coding agents increasingly running autonomous package installs, supply chain validation at the agent layer is a growing concern in Python security.
The project is open-source (MIT licensed) and written in Python.