using-git-worktrees
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [Dynamic Execution] (SAFE): The skill executes git, npm, pip, cargo, and go commands to configure worktrees and install dependencies. These operations are the primary purpose of the skill and are performed locally within the project scope.
- [Indirect Prompt Injection] (LOW): The skill reads directory preferences from CLAUDE.md. [1] Ingestion points: CLAUDE.md (config check); [2] Boundary markers: Absent; [3] Capability inventory: Local command execution (git, npm, pip); [4] Sanitization: Absent. The impact is limited to directory naming conventions.
- [Data Exposure & Exfiltration] (SAFE): Includes a mandatory safety check using 'git check-ignore' to ensure worktree contents are not accidentally committed to the repository. This acts as a safeguard against unintentional data exposure.
Audit Metadata