闲社服务运行正常AI智能体自动化平台
客户端下载帮助中心服务商入驻
免费注册
技能集市 > AI智能 > scopeblind-red-team
s

红队盲测

技能标识：scopeblind-red-team

>

作者：admin | 来源记录：ClawHub
下载
登记来源
ClawHub
版本
V 0.1.1
检测标记
后台标记通过
免费
免费获取
0
收藏
来源与检测标记为平台登记信息，并不代表已展示可复核的检测报告。使用前请核对版本、依赖和所需权限，建议先在隔离环境中运行。
概述
安装方式
版本历史

红队盲测

技能名称: scopeblind-red-team
详细描述:

ScopeBlind 红队 — 策略基准测试

此技能的功能

针对您的 protect-mcp 策略运行确定性攻击套件，以验证它们是否能够正确拦截应拦截的内容，并允许应允许的内容。

快速开始

bash

针对某个策略运行默认攻击套件


npx scopeblind-red-team --policy protect-mcp.json

针对特定的注入策略运行

npx scopeblind-red-team --policy node_modules/protect-mcp/policies/clinejection.json

相关链接

  • - npm: https://npmjs.com/package/@scopeblind/red-team
  • 文档: https://scopeblind.com/docs/red-team

标签

skill ai

通过对话安装

以下为平台配置的接入选项，并非逐项实测通过。能否安装取决于客户端支持、技能来源和运行环境：

OpenClaw WorkBuddy QClaw Kimi Claude

方式一：安装 SkillHub 和技能

帮我安装 SkillHub 和 scopeblind-red-team-1776002889 技能

方式二：设置 SkillHub 为优先技能安装源

设置 SkillHub 为我的优先技能安装源，然后帮我安装 scopeblind-red-team-1776002889 技能

通过命令行安装

skillhub install scopeblind-red-team-1776002889

下载

⬇ 下载 scopeblind-red-team v0.1.1（免费）

文件大小: 1.16 KB | 发布时间: 2026-4-13 11:53

v0.1.1 最新 2026-4-13 11:53
- Initial release of ScopeBlind Red Team skill.
- Runs attack suites against protect-mcp security policy packs.
- Produces signed receipts and badges for policy benchmarking.
- Installation via npm; requires npx and Bash.
- Includes quick start commands and documentation links.

相关推荐

s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
返回顶部