grimoire-bootstrapper

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a strict multi-step workflow (Explore, Plan, Confirm, Execute) that ensures the user reviews all proposed changes before any write operations occur.
  • [SAFE]: File modifications to agent configuration files (e.g., CLAUDE.md, AGENTS.md) are limited to appending instructions inside clearly marked comment blocks (<!-- GRIMOIRE:START --> / <!-- GRIMOIRE:END -->), which helps prevent accidental corruption of existing settings.
  • [SAFE]: The skill does not perform any network operations, download external code, or utilize sensitive system credentials. Its operations are confined to creating directories and files within the local project scope.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 04:28 AM