skills/glebis/claude-skills/cull/Gen Agent Trust Hub

cull

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill automates the Cull application by executing its local CLI binary located at /Applications/Cull.app/Contents/MacOS/cull. This binary is used for core library management tasks like importing folders, listing images, and managing collections.
  • [EXTERNAL_DOWNLOADS]: The skill includes a command, download_embedding_model, which triggers the application to fetch AI models necessary for image similarity features. This is a standard functional requirement for the application.
  • [CREDENTIALS_UNSAFE]: The skill identifies commands for managing access tokens (create_token, rotate_token, revoke_token). It includes explicit safety instructions for the agent to only use these commands when directly requested by the user, representing proper administrative control management.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 07:30 AM
Security Audit — agent-trust-hub — cull