做什么
人工智能特工的安全第一技能审查。 在安装来自 ClawdHub, GitHub 或其他来源的任何技能之前使用 。 检查红旗,许可范围,可疑图案.
技能库 智客分类:安全测试 skill-vetter OpenClaw
人工智能特工的安全第一技能审查。 在安装来自 ClawdHub, GitHub 或其他来源的任何技能之前使用 。 检查红旗,许可范围,可疑图案.
官方网址:ClawHub
先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。
人工智能特工的安全第一技能审查。 在安装来自 ClawdHub, GitHub 或其他来源的任何技能之前使用 。 检查红旗,许可范围,可疑图案.
- 在从ClawdHub安装任何技能之前
按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Skill Vetter 🔒、When to Use、Vetting Protocol、Step 1: Source Check、Step 2: Code Review (MANDATORY)、Step 3: Permission Scope。 其中含规范建议的小节:分步指令。
文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Skill Vetter 🔒When to UseVetting ProtocolStep 1: Source CheckStep 2: Code Review (MANDATORY)Step 3: Permission ScopeStep 4: Risk ClassificationOutput FormatQuick Vet CommandsCheck repo statsList skill filesFetch and review SKILL.md
来源分类:ClawHub GitHub
市场来源:ClawHub
nameskill-vetterdescription具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗
先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。
复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。
把 Agent Skill「skill-vetter」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-6fe858a1b9944d9d-%E6%8A%80%E8%83%BD%E7%BB%B4%E7%89%B9.html 请存为 .cursor/skills/skill-vetter/SKILL.md 或 .claude/skills/skill-vetter/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
当前没有明确的 GitHub 技能包地址,请按来源页面的安装器说明操作。
Security-first vetting protocol for AI agent skills. Never install a skill without vetting it first.
Questions to answer:
- [ ] Where did this skill come from?
- [ ] Is the author known/reputable?
- [ ] How many downloads/stars does it have?
- [ ] When was it last updated?
- [ ] Are there reviews from other agents?
Read ALL files in the skill. Check for these RED FLAGS:
🚨 REJECT IMMEDIATELY IF YOU SEE:
─────────────────────────────────────────
• curl/wget to unknown URLs
• Sends data to external servers
• Requests credentials/tokens/API keys
• Reads ~/.ssh, ~/.aws, ~/.config without clear reason
• Accesses MEMORY.md, USER.md, SOUL.md, IDENTITY.md
• Uses base64 decode on anything
• Uses eval() or exec() with external input
• Modifies system files outside workspace
• Installs packages without listing them
• Network calls to IPs instead of domains
• Obfuscated code (compressed, encoded, minified)
• Requests elevated/sudo permissions
• Accesses browser cookies/sessions
• Touches credential files
─────────────────────────────────────────
Evaluate:
- [ ] What files does it need to read?
- [ ] What files does it need to write?
- [ ] What commands does it run?
- [ ] Does it need network access? To where?
- [ ] Is the scope minimal for its stated purpose?
| Risk Level | Examples | Action | |------------|----------|--------| | 🟢 LOW | Notes, weather, formatting | Basic review, install OK | | 🟡 MEDIUM | File ops, browser, APIs | Full code review required | | 🔴 HIGH | Credentials, trading, system | Human approval required | | ⛔ EXTREME | Security configs, root access | Do NOT install |
After vetting, produce this report:
SKILL VETTING REPORT
═══════════════════════════════════════
Skill: [name]
Source: [ClawdHub / GitHub / other]
Author: [username]
Version: [version]
───────────────────────────────────────
METRICS:
• Downloads/Stars: [count]
• Last Updated: [date]
• Files Reviewed: [count]
───────────────────────────────────────
RED FLAGS: [None / List them]
PERMISSIONS NEEDED:
• Files: [list or "None"]
• Network: [list or "None"]
• Commands: [list or "None"]
───────────────────────────────────────
RISK LEVEL: [🟢 LOW / 🟡 MEDIUM / 🔴 HIGH / ⛔ EXTREME]
VERDICT: [✅ SAFE TO INSTALL / ⚠️ INSTALL WITH CAUTION / ❌ DO NOT INSTALL]
NOTES: [Any observations]
═══════════════════════════════════════
For GitHub-hosted skills:
# Check repo stats
curl -s "https://api.github.com/repos/OWNER/REPO" | jq '{stars: .stargazers_count, forks: .forks_count, updated: .updated_at}'
# List skill files
curl -s "https://api.github.com/repos/OWNER/REPO/contents/skills/SKILL_NAME" | jq '.[].name'
# Fetch and review SKILL.md
curl -s "https://raw.githubusercontent.com/OWNER/REPO/main/skills/SKILL_NAME/SKILL.md"
Paranoia is a feature. 🔒🦀
安全测试
MoltGuard——由OpenGuardrails担任OpenClaw保安. 安装 MoltGuard 以保护你和你的人类免受迅速注射、数据过滤和恶意命令的影响。 资料来源:https://github.com/openguardrails/openguardrails/tre…
安全测试
用于审查安全漏洞代码,实施认证流,审计OWASP Top 10,配置CORS/CSP头,处理秘密,输入验证,SQL注射预防,XSS保护,或任何与安全相关的代码审查.
安全测试
安装任何AI代理技能前的安全审查协议. 红旗侦取入证盗取,疏通密码,放出. 风险分类:低/中/高/高。 编制结构化审查报告。 不先运行此功能, 绝不安装不信任的技能 .
安全测试
系统代码审查模式涵盖安全性,性能,可维护性,正确性,以及测试——具有严重程度水平,结构化反馈指导,审查过程,以及可避免的防标. 用于审查公关,制定审查标准,或提高审查质量.