manage-worktrees
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No executable code, binary files, or suspicious scripts are bundled with this skill.
- [DATA_EXFILTRATION]: The skill performs local Git operations but contains no instructions to send data to external servers or domains.
- [PROMPT_INJECTION]: The skill instructions explicitly warn the agent to treat repository metadata, such as commit messages and hooks, as data rather than instructions, providing a layer of protection against indirect prompt injection.
Audit Metadata