介绍
# Skill Vetter 🔒
面向 AI Agent 技能的安全优先审核协议。**未经审核，绝不安装技能。**
## 何时使用
- 在从 ClawdHub 安装任何技能之前 - 在运行来自 GitHub 仓库的技能之前 - 在评估其他 Agent 共享的技能时 - 在任何被要求安装未知代码的情况下
## 审核协议
### 第 1 步：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? ```
### 第 2 步：代码审查（强制）
阅读技能中的**所有**文件。检查这些**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 ───────────────────────────────────────── ```
### 第 3 步：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? ```
### 第 4 步：风险分级
| 风险等级 | 示例 | 操作 | |------------|----------|--------| | 🟢 LOW | 笔记、天气、格式化 | 基本审查，可以安装 | | 🟡 MEDIUM | 文件操作、浏览器、API | 需要完整代码审查 | | 🔴 HIGH | 凭证、交易、系统 | 需要人工批准 | | ⛔ EXTREME | 安全配置、root 访问权限 | 绝不可安装 |
## 输出格式
审核后，生成此报告：
``` 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] ═══════════════════════════════════════ ```
## 快速审核命令
对于托管的 GitHub 技能： ```bash # 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. **OpenClaw 官方技能** → 较低审查度（但仍需审查） 2. **高星仓库（1000+）** → 中等审查度 3. **已知作者** → 中等审查度 4. **新/未知来源** → 最高审查度 5. **请求凭证的技能** → 始终需要人工批准
## 请记住
- 没有任何技能值得牺牲安全性 - 如果存疑，请不要安装 - 对于高风险决策，请询问您的人类管理员 - 记录您的审核内容以备将来参考
---
*偏执是一种特性。* 🔒🦀