groove-groovebook-review
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the official GitHub CLI (
gh) to list, view, and review pull requests. These operations are standard for development workflows and target GitHub, which is a well-known and trusted service. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted data from external sources.
- Ingestion points: Pull Request body and diff content retrieved via
gh pr viewandgh pr diffin Step 5. - Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard instructions embedded within the PR content.
- Capability inventory: The skill has the ability to write back to the repository by submitting reviews (approve, comment, request changes) via
gh pr reviewin Step 7. - Sanitization: The skill relies on the
AskUserQuestiontool to confirm the user's reaction, which serves as a human-in-the-loop safety mechanism to prevent automated obedience to instructions found in the PR content.
Audit Metadata