Open-source LLM red teaming framework. Security-test any model (Claude, GPT, Llama) for prompt injection, data leakage, etc. 15 probes, 29 prompt converters, LLM-as-judge grading, adaptive red teaming, static code audit. SARIF + JUnit for CI/CD.

Standalone AI security CTF challenges. System prompt extraction, indirect prompt injection, tool abuse, and more — local-runnable variants of the wraith.sh/academy curriculum.

When Aristotle gets a LinkedIn account and starts red-teaming LLMs. System-prompt attack surface testing using first-principles axiom framework. Load it. Ask something terrible. Watch what happens.

Provide a Python-native framework to test and audit security in large language models with coverage of key OWASP LLM risks.