Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for the agentic stack.
Latest release 1.1.1 · 23 Aug 2026
2 files for Claude Code: AgentHound CLAUDE.md, AgentHound — 1,136 tokens loaded in every session.
CLAUDE.md A 1,136 tok test-infra/services/workstation/home/.claude/settings.json A — These files are adithyan-ak/AgentHound's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.