
ai-tool-poisoning-guard
Free security-baseline rule for Claude Code, Codex, and Cursor: treats MCP tool descriptions as untrusted input (OWASP MCP Top 10 MCP03,…

Free security-baseline rule for Claude Code, Codex, and Cursor: treats MCP tool descriptions as untrusted input (OWASP MCP Top 10 MCP03,…

A structured knowledge base covering AI security fundamentals, threat modeling, red team offensive techniques, and blue team defenses, including LLM…

AI IR Overlay™ — practical incident response framework for AI agents in production. Built on NIST SP 800-61 r3, mapped to NIST AI RMF, NIST CSF 2.0,…

A practical framework identifying and prioritizing the top security risks in AI datacenter infrastructure, covering hardware, networking, management…

A curated knowledge base to build, run and mature a SOC (including CSIRT).

The OWASP Subtractive Security Top 10 Project is an initiative to identify, document, and promote the highest-impact opportunities for reducing cyber…

Sentinel detection lab for MCP attack chains: CVE-2026-26118 SSRF token theft, tool poisoning, cross-server exfiltration, identity post-exploitation.…

A TypeScript package that provides AI-powered agents for Application Security (AppSec) tasks, built on top of the frontier models.

DonkAI is a hands-on lab for the OWASP Top 10 for LLM Applications (2025) - no real LLM required.

Hands-on AI security learning platform with intentionally vulnerable LLM applications. Explore OWASP Top 10 for LLMs through interactive pizza shop…

OWASP Top 10 for Large Language Model Apps (Part of the GenAI Security Project)

Open-source cross-modal and multimodal prompt injection test suite. 250,000+ attack payloads across text, image, document, and audio modalities.…

Policy enforcement, zero-trust identity, execution sandboxing, and audit logging for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10 with…