AI Agent Security

Offensive security testing of AI agent systems covering MCP server attacks, tool poisoning, indirect prompt injection against agents, RAG knowledge base poisoning, agent sandbox escape, multi-agent compromise chains, and autonomous agent hijacking — using MCP security testers, HexStrike AI, AI-Infra-Guard, custom agent harness probes, and prompt injection toolkits.

brucesongs Updated 84 repo stars

File contents

brucesongs/kali-claw commit a3aadd2076

Frequently asked questions

npx get-skill add brucesongs/ai-agent-security