polish
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill is a legitimate orchestrator for code quality workflows. It coordinates the use of other tools and skills without introducing dangerous behaviors.
- [COMMAND_EXECUTION]: The skill executes standard Git commands (git diff, git commit, git rev-parse) and GitHub CLI commands (gh pr view) to manage branch changes and PR data. These are standard operations for a version control automation tool.
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted code from branch diffs (via git diff) and PR metadata (via gh pr view). It delegates capabilities like committing changes (git commit) and refactoring to sub-agents. The risk is mitigated by the use of internal sub-agents and high-confidence gates (>= 90%) for automated changes, but remains an ingestion point for external data into the agent's context.
- [DATA_EXFILTRATION]: No unauthorized network activity or credential access was detected. Access is limited to the local repository and the user's configured GitHub environment.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute scripts from external sources.
Audit Metadata