File contents Skill Audit 🔍
扫描 OpenClaw skills 中的安全风险,防止供应链攻击。
指令
/skill-audit scan [skill-name]
扫描已安装的 skill,检测可疑代码模式。
# 扫描所有已安装 skill
skill-audit scan
# 扫描指定 skill
skill-audit scan moltdash
# 扫描本地目录
skill-audit scan ./my-skill
/skill-audit check <clawhub-slug>
安装前检查 ClawHub 上的 skill。
skill-audit check some-skill
检测规则
🔴 高风险 (Critical)
读取凭证文件: ~/.ssh/, ~/.env, credentials.json
外发数据: fetch(), curl, webhook, POST 到未知 URL
代码执行: eval(), exec(), child_process
读取环境变量中的密钥: process.env.API_KEY
🟠 中风险 (Warning)
网络请求到非知名域名
文件系统遍历: fs.readdir(), glob
动态 require/import
Base64 编码的字符串 (可能是混淆)
🟡 低风险 (Info)
使用 shell 命令
读写用户目录外的文件
大量依赖包
输出示例
🔍 Skill Audit Report: suspicious-weather
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Risk Score: 85/100 🔴 HIGH RISK
┌─────────────┬──────────┬─────────────────────────────────┐
│ File │ Severity │ Finding │
├─────────────┼──────────┼─────────────────────────────────┤
│ index.ts │ CRITICAL │ Reads ~/.openclaw/credentials/ │
│ index.ts │ CRITICAL │ POST to webhook.site │
│ utils.ts │ WARNING │ Uses eval() │
└─────────────┴──────────┴─────────────────────────────────┘
⚠️ DO NOT INSTALL - This skill may steal your credentials!
运行方式
该 skill 附带一个 CLI 脚本,agent 可直接调用:
node {baseDir}/src/audit.js scan ~/.openclaw/workspace/skills/moltdash
node {baseDir}/src/audit.js scan --all
参考
1 --- 2 name: raini-skill-audit 3 description: Skill Audit 🔍 4 --- 5 # Skill Audit 🔍 6 7 扫描 OpenClaw skills 中的安全风险,防止供应链攻击。 8 9 --- 10 11 ## 指令 12 13 ### `/skill-audit scan [skill-name]` 14 扫描已安装的 skill,检测可疑代码模式。 15 16 ```bash 17 # 扫描所有已安装 skill 18 skill-audit scan 19 20 # 扫描指定 skill 21 skill-audit scan moltdash 22 23 # 扫描本地目录 24 skill-audit scan ./my-skill 25 ``` 26 27 ### `/skill-audit check <clawhub-slug>` 28 安装前检查 ClawHub 上的 skill。 29 30 ```bash 31 skill-audit check some-skill 32 ``` 33 34 --- 35 36 ## 检测规则 37 38 ### 🔴 高风险 (Critical) 39 - 读取凭证文件: `~/.ssh/`, `~/.env`, `credentials.json` 40 - 外发数据: `fetch()`, `curl`, `webhook`, `POST` 到未知 URL 41 - 代码执行: `eval()`, `exec()`, `child_process` 42 - 读取环境变量中的密钥: `process.env.API_KEY` 43 44 ### 🟠 中风险 (Warning) 45 - 网络请求到非知名域名 46 - 文件系统遍历: `fs.readdir()`, `glob` 47 - 动态 require/import 48 - Base64 编码的字符串 (可能是混淆) 49 50 ### 🟡 低风险 (Info) 51 - 使用 shell 命令 52 - 读写用户目录外的文件 53 - 大量依赖包 54 55 --- 56 57 ## 输出示例 58 59 ``` 60 🔍 Skill Audit Report: suspicious-weather 61 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 62 63 Risk Score: 85/100 🔴 HIGH RISK 64 65 ┌─────────────┬──────────┬─────────────────────────────────┐ 66 │ File │ Severity │ Finding │ 67 ├─────────────┼──────────┼─────────────────────────────────┤ 68 │ index.ts │ CRITICAL │ Reads ~/.openclaw/credentials/ │ 69 │ index.ts │ CRITICAL │ POST to webhook.site │ 70 │ utils.ts │ WARNING │ Uses eval() │ 71 └─────────────┴──────────┴─────────────────────────────────┘ 72 73 ⚠️ DO NOT INSTALL - This skill may steal your credentials! 74 ``` 75 76 --- 77 78 ## 运行方式 79 80 该 skill 附带一个 CLI 脚本,agent 可直接调用: 81 82 ```bash 83 node {baseDir}/src/audit.js scan ~/.openclaw/workspace/skills/moltdash 84 node {baseDir}/src/audit.js scan --all 85 ``` 86 87 --- 88 89 ## 参考 90 91 - [OWASP LLM Top 10](https://owasp.org/www-project-top-10-for-large-language-model-applications/) 92 - [Moltbook Security Discussion](https://www.moltbook.com/post/cbd6474f-8478-4894-95f1-7b104a73bcd5)
johnalbertini14-glitch/openclaw-skills/tree/main/skills/0xraini/raini-skill-audit commit 09cdccb825
Frequently asked questions How do I install the Raini Skill Audit skill? Run npx skillmds@latest add johnalbertini14-glitch/raini-skill-audit in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
What does the Raini Skill Audit skill do? Skill Audit 🔍 It is listed under Security on SkillMD.
Is Raini Skill Audit safe to use? This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: WARNING, Skill Scanner: WARNING. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
Which AI agents work with Raini Skill Audit? This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Is Raini Skill Audit free to use? Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
Who published Raini Skill Audit? johnalbertini14-glitch (@johnalbertini14-glitch) published this skill. Their other Agent Skills are listed on their SkillMD profile.