OWASP Vulnerable Web Applications Directory

An OWASP production project

A comprehensive registry of known vulnerable web and mobile applications for legal security testing and training.

AI-Goat

Learn AI/LLM security through vulnerable LLM CTF challenges. Uses Vicuna (LLaMA-derived) locally; no sign-ups or cloud fees. Aligns with OWASP Top 10 for LLM Applications; covers prompt injection, insecure output handling, data leakage, and more.

Collections offline container
Technology Python Vicuna LLM LLaMA AI
Categories CTF Single-player
Author fhammon, Guanwei Hu
Stars 340 stars
Last contribution Aug 22, 2024 < 2y

Notes

Run locally: ./ai-goat.py --install then ./ai-goat.py --run <challenge>. Optional CTFd at port 8000 (create user after launch). Requires Docker, ~8GB disk for LLM, 16GB RAM (8GB for challenge).

← Back to directory