360 Secure SkillHub
360 安全技能中心

ScopeBlind Red Team

该 Skill 是 MCP 安全策略的基准测试运行器，通过 npx 调用命令行工具，对 protect-mcp 策略包执行确定性攻击套件，检验策略是否拦截应拦截、放行应放行的行为，并生成签名回执与徽章。文档只给出运行与安装命令，未说明测试用例细节和回执验证机制。

tomjwxf
tomjwxf
热度 34.37
最近更新 2026-05-11 17:36:59
分类：安全依赖：代码执行 / 读写文件应用场景：自动化脚本 / API 集成 / 工作流

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add scopeblind-red-team
Metadata
name
scopeblind-red-team
description
Policy benchmarking runner for MCP security policies. Runs attack suites against protect-mcp policy packs, produces signed receipts and badges.
metadata
{"emoji":"⚔️","requires":{"bins":["npx"],"env":[]},"install":"npm install -g @scopeblind/red-team@latest protect-mcp@latest\n","license":"MIT","allowed-tools":["Bash","Read"]}

ScopeBlind Red Team — Policy Benchmarking

What This Skill Does

Runs deterministic attack suites against your protect-mcp policies to verify they block what they should and allow what they should.

Quick Start

# Run the default attack suite against a policy
npx scopeblind-red-team --policy protect-mcp.json

# Run against a specific incident policy
npx scopeblind-red-team --policy node_modules/protect-mcp/policies/clinejection.json

Links