soloscrum-define-code-review-process
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
gh(GitHub) CLI to perform repository management actions includinggh pr review --approve,gh pr ready, andgh pr ready --undoto automate PR lifecycle transitions. - [COMMAND_EXECUTION]: Executes the
coderabbitCLI tool (coderabbit review --plain --base main) to generate automated code review findings from a third-party service. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) as it ingests and processes data from external sources.
- Ingestion points: Review findings from CodeRabbit CLI and external multi-agent review commands are ingested into the agent context.
- Boundary markers: None identified; findings are interpolated directly into a structured PR comment format.
- Capability inventory: The skill has the capability to approve Pull Requests (
gh pr review --approve), mark them as ready (gh pr ready), and transition internal tracker states via subprocess calls. - Sanitization: No specific sanitization or filtering of the external findings' content is described before they are used to drive workflow decisions or posted as comments.
Audit Metadata