cls-certify

Solid

CocoLoop Safe (CLS) Skill 安全认证。对 Agent Skills 进行六维深度安全分析(静态代码、动态行为、依赖审计、网络流量、隐私合规、威胁情报),输出 S+/S/A/B/C/D 等级评估和 HTML/PDF 可视化报告。使用当用户需要检查 skill 安全性、验证 skill 是否可信、分析 skill 代码安全���、评估 skill 风险等级时。

Data & Documents 104 stars 6 forks Updated 1 months ago

Install

View on GitHub

Quality Score: 75/100

Stars 20%
67
Recency 20%
75
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
0
Description 5%
100

Skill Content

# CLS-Certify v2.1.0 - 下一代 Skill 安全认证 对 Agent Skills 进行企业级多维度安全检测和认证,提供 S+/S/A/B/C/D 安全等级评估,输出包含敏感风险点和外部 API 清单的结构化报告。 ## 核心能力 - **六维深度检测**: 静态分析、动态监控、依赖审计、网络分析、隐私合规、威胁情报 - **结构化报告**: 标准化 JSON/Markdown 报告,便于集成和自动化 - **供应链安全**: 检测第三方依赖的 CVE 漏洞、恶意包、typosquatting - **API 审计**: 识别并分类所有外部 API 调用,评估数据外泄风险 - **隐私合规**: GDPR、CCPA 合规性检查 ## 工作流程 ### 阶段 0: 版本检查 运行检测前,先检查 CLS-Certify 是否有新版本: ```bash bash {skill_path}/tools/check-update.sh --json > /tmp/cls-update.json ``` 读取 `/tmp/cls-update.json`,若 `update_available` 为 `true`,使用 AskUserQuestion 询问用户: ``` 使用 AskUserQuestion 询问: 问题: "CLS-Certify 有新版本可用(v{remote_version} build {remote_build}),是否先更新?" 选项: - "更新后继续" — 执行 git pull 更新后继续检测 - "跳过,使用当前版本" — 继续使用当前版本 ``` 若用户选择更新,执行 `update_command` 中的命令,然后继续检测。若检查失败或无新版本,静默跳过。 ### 阶段 1: 前置检查与来源分级 **1.1 定位 Skill** 根据用户输入确定 skill 位置: - **本地路径**: 直接使用提供的文件系统路径 - **Skill 名称**: 在 `~/.claude/skills/`、`~/.openclaw/skills/`、`~/.molili/skills/` 目录中查找 - **GitHub 链接**: 解析仓库并下载 skill 代码 - **GitHub 技能名称**: 使用 GitHub API 搜索相关技能仓库 **1.2 加载 Skill 内容** - 读取 SKILL.md 文件 - 提取 Markdown 中的所有代码块(见 1.3 节) - 检查 scripts/ 目录下的所有脚本 - 检查 references/ 目录下的所有参考文档 - 检查 assets/ 目录下的资源文件 - 检查 package.json/requirements.txt 等依赖文件 **1.3 Markdown 内嵌代码提取与分析** SKILL.md 中的代码块需要单独提取和安全检查: **提取范围**: - 所有带语言标记的代码块(```language...```) - 可执行语言:bash/shell、python、javascript、typescript **风险分级**: - **低风险**: 配置文件、代码片段演示、单行无害命令 - **中风险**: 可执行脚本、网络请求、文件操作 - **高风险**: 危险函数(eval/exec)、系统破坏性命令、硬编码密钥 **1.4 来源可信度评估 (T1/T2/T3...

Details

Author
CatREFuse
Repository
CatREFuse/cls-certify
Created
2 months ago
Last Updated
1 months ago
Language
Shell
License
None

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

skill-vetter

Multi-scanner security gate. TRIGGER when: user mentions installing, adding, or reviewing a skill to Claude Code, OpenClaw, or any other AI agent. Detects malicious code, vulnerabilities, and suspicious patterns.

32 Updated 2 months ago
app-incubator-xyz
DevOps & Infrastructure Solid

node.js-

检查 RCE、SSRF、SQL 注入、路径穿越等安全问题,支持 Express/Koa/NestJS

833 Updated 3 days ago
TencentBlueKing
DevOps & Infrastructure Listed

code-audit

Professional code security audit skill covering 55+ vulnerability types. Enhanced with WooYun 88,636 real-world vulnerability cases (2010-2016). This skill should be used when performing security audits, vulnerability scanning, penetration testing preparation, or code review for security issues. Supports 9 languages: Java, Python, Go, PHP, JavaScript/Node.js, C/C++, .NET/C#, Ruby, Rust. Includes 143 mandatory detection items across all languages with language-specific checklists. Covers SQL injection, XSS, RCE, deserialization, SSRF, JNDI injection, JDBC protocol injection, authentication bypass, business logic flaws, race conditions, and modern security domains (LLM, Serverless, Android). WooYun integration adds: statistical-driven parameter priority, bypass techniques library, logic vulnerability patterns, and real-case references. v1.0: Initial public release with Docker deployment verification framework.

704 Updated 3 months ago
3stoneBrother
Data & Documents Solid

skill-issue

Audit and review all installed agent skills. Run on-demand or via cron to get a health report: skill inventory, usage tracking, version checks, dependency health, and actionable recommendations (keep, update, review, remove). Use when asked to review skills, check for skill updates, find unused skills, or audit the skill ecosystem.

23 Updated 3 months ago
krispuckett
AI & Automation Listed

verification

Path-conditional verification checklist (basic/standard/strict) with retry loop

175 Updated today
WenJunDuan