shiva108/ai-llm-red-team-handbook

The AI/LLM Red Team Handbook is a comprehensive operational toolkit designed for security professionals to conduct red team assessments on Large Language Models, AI agents, RAG pipelines, and AI-enabled applications. It provides both tactical field guidance and strategic consulting frameworks, featuring a 46-chapter curriculum covering prompt injection, jailbreaking, adversarial machine learning, and compliance with regulations like the EU AI Act.