user1342/Awesome-LLM-Red-Teaming

A curated list of awesome LLM Red Teaming training, resources, and tools.

42
/ 100
Emerging

This resource helps security researchers, AI developers, and auditors identify and exploit vulnerabilities in large language models (LLMs). It provides a curated collection of tools, guides, and research for conducting red-teaming exercises. You'll find resources ranging from practice environments for prompt injection to advanced frameworks for automated adversarial testing, allowing you to expose weaknesses in LLM security and alignment.

No commits in the last 6 months.

Use this if you need to systematically test the security, robustness, and ethical alignment of LLM-powered applications through adversarial attacks and vulnerability research.

Not ideal if you are looking for resources on general LLM development, fine-tuning, or application building, as its focus is exclusively on security and exploitation.

AI security red teaming vulnerability research LLM auditing prompt engineering
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

83

Forks

12

Language

License

MIT

Last pushed

Sep 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/user1342/Awesome-LLM-Red-Teaming"

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