0xalexhex/redjudge
Open-source red-team harness for LLMs. Jailbreaks, prompt injection, agentic tool-abuse and image attacks, scored with validated judges (Llama Guard 3, StrongREJECT).
GitHub repository with 8 stars and 0 forks.
Language: Python
Topics: adversarial-ml, ai-safety, ai-security, jailbreak, llama-guard, llm, llm-security, model-evaluation, prompt-injection, red-teaming