← 返回 Skills 市场
Security Audit
作者
chandrasekar-r
· GitHub ↗
· v1.0.0
13225
总下载
8
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install security-audit
功能描述
Comprehensive security auditing for Clawdbot deployments. Scans for exposed credentials, open ports, weak configs, and vulnerabilities. Auto-fix mode included.
安全使用建议
Review this skill before installing. Use it only in an environment where reading Clawdbot secrets and project files under /root/clawd is acceptable, and avoid running --fix as root or on production systems unless you have backups and are prepared for recursive permission changes to JSON, env, key, and PEM files.
功能分析
Type: OpenClaw Skill
Name: security-audit
Version: 1.0.0
The OpenClaw AgentSkills skill bundle is designed for comprehensive security auditing of Clawdbot deployments. The `SKILL.md` instructions clearly outline its purpose and usage, including options for scanning credentials, ports, configurations, and permissions, as well as an auto-fix mode. The core script, `scripts/audit.cjs`, uses `child_process.execSync` to run system commands like `ss` or `netstat` for port scanning and `git log` for commit history, which are legitimate actions for a security audit tool. It also uses `fs` module functions to read files and scan for sensitive patterns (e.g., API keys, passwords) within the defined `CLAWDBOT_DIR` (`/root/clawd`). Crucially, while it identifies sensitive data, there is no evidence of data exfiltration to external endpoints. The auto-fix functionality (`fs.chmodSync`, `fs.writeFileSync`) is used to harden security by setting restrictive file permissions and creating a `.gitignore` file. No prompt injection attempts against the agent, obfuscation, or other malicious indicators were found; the behavior is entirely aligned with its stated security auditing purpose.
能力评估
Credentials
Reading deployment secrets is coherent for a security audit, but the hardcoded root deployment directory and recursive scanning are overbroad for users who may have unrelated projects or credentials under the same tree.
Install Mechanism
The artifact contains a markdown skill file and one local Node.js script, with no external dependency installation, remote payload retrieval, or install-time execution found.
Instruction Scope
The instructions disclose credential scans and auto-fix mode, but they do not clearly warn that --fix recursively chmods all .env, .json, .key, and .pem files under /root/clawd or provide target scoping, dry-run, confirmation, or rollback guidance.
Persistence & Privilege
No daemon, scheduled task, or backdoor persistence was found, but --fix makes lasting permission changes and writes a .gitignore under /root/clawd without confirmation or rollback metadata.
Purpose & Capability
Credential scanning, port checks, config checks, Docker checks, and permission checks fit the stated security-audit purpose, but the implementation uses hardcoded /root/clawd paths and can inspect sensitive .env/config files and recursively process many project files.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install security-audit - 安装完成后，直接呼叫该 Skill 的名称或使用
/security-audit触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
更新日志
Initial release: credential scanning, port detection, config validation, file permissions, Docker security checks, auto-fix mode
元数据
常见问题
Security Audit 是什么？
Comprehensive security auditing for Clawdbot deployments. Scans for exposed credentials, open ports, weak configs, and vulnerabilities. Auto-fix mode included. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 13225 次。
如何安装 Security Audit？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install security-audit」即可一键安装，无需额外配置。
Security Audit 是免费的吗？
是的，Security Audit 完全免费（开源免费），可自由下载、安装和使用。
Security Audit 支持哪些平台？
Security Audit 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Security Audit？
由 chandrasekar-r（@chandrasekar-r）开发并维护，当前版本 v1.0.0。
推荐 Skills