Tool · curated 29 Jul 2026
GitHub - 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.
First reported github.com
Coverage timeline
Single-source analysis — first reported, latest, and curated coincide.
Why it matters
AgentHound gives red-teamers and defenders a purpose-built framework to map and test attack paths across MCP, A2A, and gateway components of agentic AI deployments, surfacing risks like credential theft and model exfiltration before adversaries exploit them.
AgentHound is an open-source offensive security framework for AI agent infrastructure, described as "BloodHound for the agentic stack." The tool performs reconnaissance, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services.