skills/openclaw/skills/file-cleaner/Gen Agent Trust Hub

file-cleaner

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill enforces a strict whitelist for file operations, limiting deletions to 'temp/', 'logs/', and 'cache/' directories relative to the workspace root.
  • [SAFE]: Path traversal attacks are mitigated through the use of path.resolve(), which normalizes user-provided input before validating it against the allowed prefixes.
  • [SAFE]: Explicit checks are included to prevent the deletion of critical directories such as the workspace root and the 'skills/' directory itself.
  • [SAFE]: The code uses only built-in Node.js modules (fs and path) and contains no external dependencies, remote code downloads, or network communication.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:52 PM