AgentHound

Offensive security framework for AI agent infrastructure — recon, credential looting, attack paths.

Pluginfreeglobal

AgentHound is an open-source offensive security framework for AI agent infrastructure — described as 'BloodHound for the agentic stack' — running recon, credential looting, model and prompt inventory, and attack-path graphing across MCP, A2A, gateways, inference servers, and vector stores. It explicitly restricts use to infrastructure the operator owns or is written-authorized to assess, and is for red teams and security researchers mapping attack paths in modern AI agent deployments.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of AgentHound - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim AgentHound to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether AgentHound (or something else) actually fits.

Try a problem