name: security-audit description: "Comprehensive OpenClaw security audit — checks gateway binding, credential exposure, channel policies, tool sandboxing, network/IP leaks, and macOS system security (SIP, FileVault, TCC)." version: 1.0.0 metadata: openclaw: emoji: "\U0001F512" os: - macos - linux homepage: https://github.com/sunt23310-ops/openclaw-security-audit requires: anyBins: - python3 - python bins: - bash - curl install: - kind: brew formula: python3 bins: - python3
Run a comprehensive security audit on your local OpenClaw installation. Covers 6 security domains mapped to MITRE ATLAS threat categories.
Check if the audit tool is installed:
小蔥技能7w4.net持續更新中。
ls ~/openclaw-security-audit/audit.sh 2>/dev/null || echo "NOT_INSTALLED"
If not installed, clone it:
git clone https://github.com/sunt23310-ops/openclaw-security-audit.git ~/openclaw-security-audit
AUDIT_DIR="$HOME/openclaw-security-audit"
bash "$AUDIT_DIR/checks/gateway.sh" && bash "$AUDIT_DIR/checks/credentials.sh"
for check in gateway credentials channels tools network system; do
bash "$AUDIT_DIR/checks/${check}.sh"
done
Match the user's concern to the right module:
| User asks about | Command |
|---|---|
| Gateway, ports, binding, auth, TLS | bash "$AUDIT_DIR/checks/gateway.sh" |
| API keys, passwords, file permissions, history leaks | bash "$AUDIT_DIR/checks/credentials.sh" |
| WhatsApp, Telegram, DM policy, allowFrom | bash "$AUDIT_DIR/checks/channels.sh" |
| Sandbox, denyCommands, tool restrictions | bash "$AUDIT_DIR/checks/tools.sh" |
| IP leak, exposed ports, firewall, Shodan/Censys | bash "$AUDIT_DIR/checks/network.sh" |
| macOS SIP, FileVault, TCC, iCloud sync | bash "$AUDIT_DIR/checks/system.sh" |
bash "$AUDIT_DIR/fixes/interactive-fix.sh"
Specific fixes:
- bash "$AUDIT_DIR/fixes/gateway-fix.sh" — bind gateway to localhost, generate strong token
- bash "$AUDIT_DIR/fixes/permission-fix.sh" — fix file/directory permissions
- bash "$AUDIT_DIR/fixes/channel-fix.sh" — fix DM policy, allowFrom, requireMention
bash "$AUDIT_DIR/audit.sh"
Then select option 5 for HTML or JSON report output.
Each check outputs lines prefixed with:
- [PASS] — check passed, no action needed
- [WARN] — potential issue, review recommended
- [FAIL] — security issue found, fix recommended
- [SKIP] — check skipped (component not installed or not applicable)
After running checks, summarize results clearly. If there are FAIL items, recommend the appropriate fix script and explain what it will do before the user confirms.
這個 Skill 質量不錯,文件清晰易懂,能幫助使用者檢查 OpenClaw 的安全問題並提供修復建議。優點是覆蓋全面、操作明確、有自動修復功能;不足是完全依賴外部工具,沒有內建實現,離線環境下無法使用。對於需要安全審計的使用者來說是一個實用的工具。