autolearn-curator

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses uv run to execute a local Python script (autolearn.py) located in the agent's internal directory. These commands are used to list, analyze usage, and archive skills as part of regular library maintenance.
  • [SAFE]: The operations are restricted to the $HOME/.autolearn/skills/ directory and manage only skills identified as being created by the system. It does not perform network requests or access sensitive user data like credentials or SSH keys.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 12:39 PM
Security Audit — agent-trust-hub — autolearn-curator