lov-gh-tidy
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
ghandgitcommand-line interfaces for repository management. These commands (e.g.,gh issue close,gh pr merge,git push origin --delete) are standard for the intended workflow and are only executed following user-approved triage decisions.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted input from GitHub issues and PRs. The risk of the agent following instructions embedded in issue titles or PR bodies is mitigated by a mandatory human-in-the-loop triage process. The agent is required to present an analysis of each item to the user and obtain explicit confirmation viaAskUserQuestionbefore performing any write operations.
Audit Metadata