Agent Infrastructure · Curated marketplace
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…
Composite
3.7
C 3.7 · A 0.0
How we got there
1 source verified
- Best source
skillsmp.com - Authority tier Tier 2 — Curated marketplace
- Stars ★ 1,302
- Source link https://skillsmp.com/skills/wgpsec-aboutsecurity-skills-ai-security-mcp-security-skill-md ↗
- First published 2026-05-24
Use this skill
/plugin install mcp-securityMore in Agent Infrastructure
skill-creator
Create, edit, improve, or audit AgentSkills.
mcp-sentinel
Security monitoring agent for Claude Skills and MCP servers.
exploring-llm-traces
ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools.
define-goal
Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy…
Auto-indexed. Editorial review pending — score is based on the rubric only.