DmitrL-dev/AISecurity

AIGoat - Open-source AI security playground for hands-on LLM red teaming. Explore prompt injection, RAG poisoning, AI agents, MCP security, and OWASP Top 10 for LLM Applications through practical attack labs, CTF challenges, and progressive defenses all running locally.

A live environment to stress-test AI agent defenses through adversarial play 🧠

Damn Vulnerable AI Agent is a deliberately vulnerable AI agent platform for security testing and education.

A curated list of AI Security materials and resources for Pentesters, Bug Hunters, and Security Researchers.

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.

Curated resources, research, and tools for securing AI systems

Demos for Practical AI Security by No Starch Press

Set of tools to assess and improve LLM security.

SecCodeBench is a benchmark suite focusing on evaluating the security of code generated by large language models (LLMs).