skill-vetter

技能审查 🔒

面向 AI Agent 技能的安全优先审查协议。未经审查，切勿安装技能。

适用场景

• 从 ClawdHub 安装任何技能之前
• 运行 GitHub 仓库中的技能之前
• 评估其他 Agent 分享的技能时
• 任何被要求安装未知代码的情况

审查协议

步骤 1：来源检查

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?

步骤 2：代码审查（必做）

阅读技能中的所有文件。检查以下危险信号：

🚨 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
─────────────────────────────────────────

步骤 3：权限范围

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?

步骤 4：风险分类

风险级别	示例	操作
🟢 低	笔记、天气、格式整理	基本审查，可以安装
🟡 中	文件操作、浏览器、API	必须进行完整代码审查
🔴 高	凭据、交易、系统	必须获得人工批准
⛔ 极高	安全配置、root 访问权限	切勿安装

输出格式

审查后，生成以下报告：

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]
═══════════════════════════════════════

快速审查命令

针对托管在 GitHub 上的技能：

# 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"

信任层级

1. 官方 OpenClaw 技能 → 审查力度较低（仍需审查）
2. 高星级仓库（1000+） → 适度审查
3. 已知作者 → 适度审查
4. 新来源/未知来源 → 最严格审查
5. 请求凭据的技能 → 始终需要人工批准

记住

• 没有任何技能值得以牺牲安全为代价
• 如有疑虑，不要安装
• 高风险决策请咨询人工
• 记录审查结果，供将来参考

---

偏执是一项特性。 🔒🦀