SecureClaw - Security Plugin and Skill for OpenClaw OWASP-Aligned

Code scanner to check for issues in prompts and LLM calls

LMAP (large language model mapper) is like NMAP for LLM, is an LLM Vulnerability Scanner and Zero-day Vulnerability Fuzzer.

Static security scanner for AI agents. Catches prompt injection, runaway loops, missing oversight, and compliance gaps across 21 frameworks. Use from Claude Code, Cursor, ChatGPT (MCP), the CLI, or GitHub Actions.

AI security and prompt injection payload toolkit

An intentionally vulnerable AI chatbot to learn and practice AI Security.

Basilisk — Open-source AI red teaming framework with genetic prompt evolution. Automated LLM security testing for GPT-4, Claude, Grok, Gemini. OWASP LLM Top 10 coverage. 32 attack modules.

A purposely vulnerable voice agent application for security practitioners to practice exploiting voice-based (and text based) AI systems.

AIDEFEND MCP is a local-first AI Security Defensive Assistant that brings the full AIDEFEND countermeasure library into your environment and turns static knowledge into actionable protection for LLMs and agentic AI systems — privately, securely, and on-device.

Open-Source Prompt Injection Scanner for AI agents. 225 detection patterns, 15 languages, F1=98.3%. REST API, EU AI Act compliance mapping, <10ms latency.

OWASP LLM Top 10 (2025) Türkçe Kapsamlı Rehber. Büyük Dil Modelleri (LLM) için en kritik 10 güvenlik riskini, gerçek saldırı senaryolarını ve savunma stratejilerini içeren teknik dökümantasyon. Türkiye'nin ilk LLM Security yazı serisinin 3. bölümü.

Türkiye'nin ilk ve en kapsamlı Yapay Zeka Güvenliği (AI Security) serisi. Prompt Injection'dan otonom ajan güvenliğine, teknik rehberler ve 2026 uzmanlık yol haritası. AltaySec tarafından hazırlanmıştır.

AI security testing engine for surfacing prompt leaks, bypasses, and unsafe agent behavior.

GenAI-ML-SecAudit is an implementation of OWASP 2025 Top 10 for LLMs and Gen AI Apps risks. The tool simulate attacks, capture logs, and generate an interactive HTML graph that visualizes the results.

The Citadel is not just a training platform; it is a battleground. As AI systems integrate deeper into our critical infrastructure, the attack surface expands exponentially. This application is a purpose-built LLM Pentesting Environment designed to simulate real-world threats against Large Language Models.

750-example security training dataset for AI coding assistants covering OWASP LLM Top 10 2025 with secure code patterns

this is a discovery i made and reported through the proper security channels.

Zero-dep TypeScript prompt-injection firewall: block/excise/quarantine/tag modes, Unicode Plane 14, encoding-bypass resistance (leet/base64/ROT13), output exfil + canary validation. OWASP LLM01/ASI01.

Adversarial testing and red-teaming framework for enterprise LLM deployments. Covers OWASP LLM Top 10 across 11 attack modules, RAG poisoning, tool-call abuse, PII leakage, credential harvesting, hallucination, and more. Built to run in CI/CD pipelines.

AI Security Maturity Model and assessment toolkit—secure models, data, LLM/RAG, infra, monitoring, and IR across 11 domains and 5 levels, aligned to NIST AI RMF, SAIF, and OWASP LLM Top 10.