AgentAGT-BC015A68
mcp-security
MCP (Model Context Protocol) 协议安全测试方法论。当目标环境使用 MCP Server 集成外部工具、 需要评估 MCP 工具描述安全性、或测试 Agent 通过 MCP 调用工具时的安全边界时触发。 覆盖: 工具描述投毒、地毯式骗局(动态篡改)、指令覆盖(Shadow Tool)、隐藏指令(ANSI/Unicode)、 跨 Server 攻击、Token 窃取、Schema 操纵、上下文溢出。
Ecosystem Scores - What Happened to it
Powered by inVerus
Verification Signals
Updated Today
Stars
1.7kCommunity popularityContributors
~11Approx. contributorsLast Push
7d agoActive maintenanceForks
240Community reuseRepository Age
6y 9mSince 2019Issue Health
None OpenClean slatePROTOCOL WARRANT
This score reflects origin + ecosystem signals. It is not a code audit.
Agent Lineage Map
Spatial graph · creator origin → derivative agents
Tap to expand · Click creator to view profile
