deepsafe-scan

<p align="center">
  <img src="docs/logo.png" alt="DeepSafe Scan" width="180">
</p>

<h1 align="center">DeepSafe Scan</h1>

<p align="center">
  <strong>AI Agent 环境通用安全预检扫描器</strong>
</p>

<p align="center">
  <a href="https://python.org"><img src="https://img.shields.io/badge/python-3.9%2B-blue.svg" alt="Python"></a>
  <a href="#零依赖"><img src="https://img.shields.io/badge/依赖-零-green.svg" alt="零依赖"></a>
  <a href="https://clawhub.ai"><img src="https://img.shields.io/badge/ClawHub-deepsafe--scan-orange.svg" alt="ClawHub"></a>
  <a href="https://xiaoyiweio.github.io/deepsafe-scan/"><img src="https://img.shields.io/badge/在线文档-GitHub%20Pages-blue?logo=github" alt="GitHub Pages"></a>
</p>

<p align="center">
  <a href="https://xiaoyiweio.github.io/deepsafe-scan/">
    <strong>📖 完整文档与演示 → xiaoyiweio.github.io/deepsafe-scan</strong>
  </a>
</p>

<p align="center">
  <em>运行前先扫描。一条命令，保护你的 AI Agent 环境免受密钥泄露、提示词注入、Hooks 后门攻击。</em>
</p>

<p align="center">
  想了解这些攻击是怎么运作的？→ <a href="https://github.com/XiaoYiWeio/ai-agent-attack-techniques"><strong>AI Agent Attack Techniques</strong></a>
</p>

---

<p align="center">
  <strong>⚡ 攻击者只需 3 秒，就能从你的 AI Agent 环境中窃走 SSH Key、API Key 和全部敏感凭证。</strong><br>
  <sub>↓ 真实攻击演示（3 倍加速）&nbsp;·&nbsp;<a href="https://xiaoyiweio.github.io/deepsafe-scan/#demo">观看完整原速视频 →</a></sub>
</p>

<p align="center">
  <img src="docs/demo.gif" alt="3秒窃取你的全部凭证 - DeepSafe Scan 攻击演示" width="800">
</p>

<p align="center">
  <sub>你 clone 的下一个仓库，可能已经在等你打开它了。</sub>
</p>

---

<p align="center">
  <strong>支持平台：</strong>&nbsp;&nbsp;&nbsp;
  <img src="docs/openclaw.svg" alt="OpenClaw" width="48" valign="middle">&nbsp;<strong>OpenClaw</strong>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
  <img src="docs/claudecode-color.svg" alt="Claude Code" width="40" valign="middle">&nbsp;<strong>Claude Code</strong>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
  <img src="docs/cursor.svg" alt="Cursor" width="40" valign="middle">&nbsp;<strong>Cursor</strong>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
  <img src="docs/codex-col