What problem does it solve?
Review security of command execution, tool permissions, and API key handling. Use when user mentions "security review", "audit", "check security", "vulnerabilities", or before deploying to production.
Core Features & Use Cases
- Command Execution Review (backend/main.py):
- Check
run_terminal_command() for shell injection vulnerabilities
- Verify timeout is enforced (should be 15 seconds)
- Look for dangerous command patterns
- Tool Permission Review:
- Verify Chat mode only allows:
read_file, web_search
- Check Agent mode tool restrictions
- Look for permission bypass vulnerabilities
- Secrets Management:
- Ensure
.env is in .gitignore
- Check no API keys are hardcoded
- Verify
python-dotenv usage for environment variables
- WebSocket Security:
- Check for authentication on
/ws endpoint
- Review message validation
- Look for injection points in user input
- Frontend Security:
- Check for XSS in markdown rendering
- Review image upload handling (base64 encoding)
- Verify no sensitive data in client-side code
Quick Start
Run the security audit to generate a report; this is READ-ONLY, so do not modify files automatically. Propose fixes and ask for approval before applying changes.
- Examples
- "Run a security audit"
- "Check for vulnerabilities"
- "Review security before deploy"