@tank/git-worktrees

Pass

Audited by Gen Agent Trust Hub on May 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is primarily documentation and instructional content focused on the standard Git worktree feature.
  • [COMMAND_EXECUTION]: The skill provides numerous shell command templates and helper functions (e.g., wt-new, wt-done). These are standard Git, NPM, and Pip operations appropriate for the described developer workflows (hotfixes, PR reviews, etc.).
  • [EXTERNAL_DOWNLOADS]: References are made to official Git documentation and well-known developer tools like git-worktree.nvim. Suggested commands include standard git clone and package installations (npm install), which are typical for project setup.
  • [DATA_EXFILTRATION]: The skill configuration in tank.json explicitly denies outbound network access and restricts filesystem access to read-only for the project workspace, providing a high level of isolation.
  • [PROMPT_INJECTION]: No malicious patterns or attempts to override system instructions were found. The instructional tone is helpful and follows Git best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
May 31, 2026, 11:04 PM
Security Audit — agent-trust-hub — @tank/git-worktrees