dhammon/ai-goat

Learn AI security through a series of vulnerable LLM CTF challenges. No sign ups, no cloud fees, run everything locally on your system.

45
/ 100
Emerging

This project offers a hands-on way for security professionals and developers to learn about vulnerabilities in AI large language models (LLMs). It provides a series of local, self-contained "capture the flag" challenges where you interact with a simulated vulnerable LLM, identify security flaws, and find hidden "flags." This is ideal for security teams looking to enhance their practical skills in LLM security.

325 stars. No commits in the last 6 months.

Use this if you need practical, offline training to understand and mitigate common security risks in applications powered by large language models.

Not ideal if you're looking for a simple LLM development library or a tool for general application security testing unrelated to AI.

AI-security-training LLM-vulnerability-assessment cybersecurity-education threat-hunting application-security
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

325

Forks

46

Language

Python

License

GPL-2.0

Last pushed

Aug 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/dhammon/ai-goat"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.