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.
Last push 6 days ago
a2a
agentic-ai
ai-agents
ai-security
attack-paths
bloodhound
llm-security
mcp
model-context-protocol
neo4j
offensive-security
pentesting
red-team
security-tools
Created
Apr 2026
Total stars
464
Last 7 days
+1
Last 30 days
+11
Last 12 months
+464
README badge
[](https://bestofgo.dev/adithyan-ak/AgentHound)