AgentHound
未认领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.
a2aagentic-aiai-agentsai-securityattack-pathsbloodhoundllm-securitymcpmodel-context-protocolneo4joffensive-securitypentestingred-teamsecurity-tools
安装
$
go install github.com/adithyan-ak/agenthound/collector/cmd/agenthound@1.0.0更多Security服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理