continuous-learning

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill documentation provides instructions for users to manually add a hook to their configuration file. This hook executes a local script, evaluate-session.sh, when a session stops.
  • [SAFE]: The evaluate-session.sh script accesses the session transcript via the CLAUDE_TRANSCRIPT_PATH environment variable. It uses this to count user interactions and determine if the session meets the minimum length requirement for pattern extraction.
  • [SAFE]: The skill manages a local directory at ~/.claude/skills/learned/ for storing results. It does not perform any network operations or external data transmissions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 08:24 PM