ClaudeWave
XiaoYiWeio
XiaoYiWeio

deepsafe-scan

View on GitHub

Universal preflight security scanner for AI coding agents — Detects hooks injection, credential exfiltration & backdoors in .cursorrules, CLAUDE.md, AGENTS.md and more.

Subagents62 stars9 forksPythonUpdated 5d ago
ClaudeWave Trust Score
62/100
· OK
Passed
  • Actively maintained (<30d)
  • Clear description
  • Topics declared
Flags
  • !No license declared
Last scanned: 4/14/2026
Install in Claude Desktop
Method detected: Manual
{
  "mcpServers": {
    "deepsafe-scan": {
      "command": "node",
      "args": ["/path/to/deepsafe-scan/dist/index.js"]
    }
  }
}
1. Copy the snippet above.
2. Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (Mac) or %APPDATA%\Claude\claude_desktop_config.json (Windows).
3. Replace any <placeholder> values with your API keys or paths.
4. Restart Claude Desktop. The MCP server appears automatically.
💡 Clone https://github.com/XiaoYiWeio/deepsafe-scan and follow its README for install instructions.
Use cases
🔐 Security🧠 AI / ML

Subagents overview

README preview not available. Visit the repo on GitHub for full documentation.
ai-agentsaisecurityclaudeclaude-codecodexcursoropenclawopenclaw-pluginopenclaw-skillopenclaw-skillsprompt-injectionprompt-injection-llm-securitysafety

More Subagents