grimoire-init
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows a secure 'propose-verify-apply' workflow. It requires explicit user approval before writing any files or modifying existing project configuration. This significantly reduces the risk of accidental or malicious automated changes.
- [SAFE]: File operations are restricted to project-relevant files such as
.grimoire/directories,AGENTS.md, andCLAUDE.md. It does not attempt to access sensitive system files, environment variables, or credentials. - [SAFE]: Use of Git commands (
git check-ignore,git ls-files) is limited to verifying state and policy enforcement. There are no patterns of remote code execution or shell injection. - [SAFE]: The skill includes instructions to handle malformed markers and conflicts safely, reporting them to the user rather than making assumptions or overwriting content blindly.
Audit Metadata