branch-cleanup
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill utilizes standard git and GitHub CLI (gh) commands. It avoids dangerous flags like force-delete (-D) and uses --ff-only for pulls to prevent accidental merge conflicts or state corruption.
- [DATA_EXFILTRATION] (SAFE): No sensitive data access or external exfiltration patterns were detected. All network operations are directed at the user's configured git origin or GitHub API via official tools.
- [PROMPT_INJECTION] (SAFE): The instructions do not contain attempts to override agent behavior, bypass safety filters, or extract system prompts.
- [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill processes external data (PR titles and branch names), the risk is mitigated by hardcoded branch protection (e.g., main, master) and a mandatory human-in-the-loop confirmation step before any action is taken.
Audit Metadata