adithyan-ak/agenthound

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.

2 best points · 0 comments · 1 Hacker News post · 461 GitHub stars · View on GitHub

Hacker News discussions

• Agenthound – Offensive security framework for AI agent infrastructure (2 points, 0 comments, by akoffsec, 2026-07-28)