LLM Red Team

LLM and generative AI red team testing covering prompt injection, jailbreaking (DAN, many-shot, Crescendo, PAIR/TAP, GCG suffix, persona modulation, prefix injection, payload smuggling), model extraction, RAG poisoning, agentic tool abuse, and safety policy bypass using promptfoo, garak, PyRIT, PurpleLlama, AI-Infra-Guard and llm-guard — plus Constitutional AI, Llama Guard, NeMo Guardrails, and Azure AI Content Filter evasion.

brucesongs Updated 84 repo stars

File contents

brucesongs/kali-claw commit cb339a7564

Frequently asked questions

npx get-skill add brucesongs/llm-red-team