gh-fix-ci
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- Command Execution via Subprocess: The skill includes a bundled Python script,
scripts/inspect_pr_checks.py, which executesgh(GitHub CLI) andgitcommands usingsubprocess.run. These operations are used to retrieve pull request metadata, check statuses, and logs. The implementation uses list-based arguments rather than shell strings, which is a recommended practice to minimize risk. - Indirect Prompt Injection Surface: The skill processes external data, such as GitHub Actions logs and PR metadata. While this represents a surface where untrusted content could be ingested into the agent's context, the skill's instructions emphasize summarizing findings and proposing plans for explicit user approval before taking action.
- Credential Management: The workflow relies on the user's existing GitHub CLI authentication. It includes checks like
gh auth statusto ensure the environment is ready and provides clear instructions for the user to log in manually if needed, maintaining transparency and user control over credentials.
Audit Metadata