Vrishinram/GuardRift

⚡ Automated LLM Jailbreak Evaluation Suite & red-teaming framework to benchmark AI safeguard robustness.

adversarial-robustness ai-red-teaming ai-safety infosec jailbreak-evaluation llm-evaluation pydantic-v2 python

1 Open Issue Need Help Last updated: Sep 3, 2026

Open Issues Need Help

documentation help wanted good first issue

⚡ Automated LLM Jailbreak Evaluation Suite & red-teaming framework to benchmark AI safeguard robustness.

Python

#adversarial-robustness#ai-red-teaming#ai-safety#infosec#jailbreak-evaluation#llm-evaluation#pydantic-v2#python