managing-git-worktrees
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell-based Git commands to manage worktree lifecycles. It explicitly instructs the agent to treat dynamic references and paths as untrusted data, requiring validation and proper quoting to prevent command injection vulnerabilities.
- [PROMPT_INJECTION]: While the skill processes external data such as branch names and worktree lists which could be vectors for indirect prompt injection, it mitigates this by mandating the use of Git's internal validation mechanisms (e.g.,
git check-ref-format --branch) and porcelain output parsing with null-termination (-z) to ensure data integrity. - [DATA_EXPOSURE]: The skill interacts with local repository metadata but does not access sensitive user directories (like
.sshor.aws) or perform any network-based exfiltration. It handles user data with care, requiring explicit confirmation before deleting or pruning unmerged data.
Audit Metadata