name: skill_guard description: "Skill Security Scanner - Scan for risks before download/use. Use when: installing unknown skills, evaluating third-party code, or security auditing. / Skill安全檢查 - 下載/使用前檢測風險。" metadata: author: "WaaiOn" version: "1.2" openclaw: emoji: "🛡️" requires: bins: ["python3"]
Security scanner for AI Skills. Check code safety before install or use.
| EN | CN |
|---|---|
| Installing unknown skills | 安裝未知來源的skill |
| Evaluating third-party code | 評估第三方程式碼 |
| Security auditing | 安全審計 |
| Before running untrusted code | 執行不受信任的程式碼前 |
| Category | EN | CN | Severity |
|---|---|---|---|
| Code Execution | 程式碼執行 | 🔴 Critical | |
| File Deletion | 檔案刪除 | 🔴 Critical | |
| Command Injection | 命令注入 | 🔴 Critical | |
| Credential Leak | 憑證洩露 | 🟠 High | |
| Network Request | 網路請求 | 🟠 High | |
| Data Theft | 竊取資料 | 🔴 Critical | |
| Induce Transfer | 誘導轉錢 | 🔴 Critical | |
| Virus/Backdoor | 病毒/後門 | 🔴 Critical |
# Scan local skill / 掃描本地skill
python3 -c "from skill_guard import scan; print(scan('/path/to/skill'))"
# Inspect remote / 檢查遠端
python3 -c "from skill_guard import inspect_remote; print(inspect_remote('skill-name'))"
RISK_PATTERNS = {
'code_execution': ['exec(', 'eval(', 'compile(', '__import__'],
'file_deletion': ['rm -rf', 'shutil.rmtree', 'os.remove'],
'command_injection': ['subprocess', 'os.system', 'shell=True'],
'credential_leak': ['password', 'api_key', 'token', 'secret'],
'data_theft': ['/etc/passwd', '~/.ssh', 'clipboard'],
'induce_transfer': ['alipay', 'bank_card', 'payment'],
'virus_backdoor': ['ransomware', 'miner', 'backdoor'],
}
npx clawhub install skill-guard-waai
來源於7w4.net。
這是一款專門用於檢查 Skill 程式碼安全性的工具,檢測範圍涵蓋程式碼執行、檔案刪除、憑證洩露、網路請求等常見風險,掃描覆蓋面較廣。文件編寫規範,支援中英文切換。不足之處是功能相對基礎,缺少遠端檢查等高階功能,且沒有提供實際使用示例,對於不熟悉程式碼的使用者來說上手可能有一定門檻。整體質量中規中矩,適合對安全性有基本需求的場景使用。