github-review-pr
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The agent is instructed to use the GitHub CLI (gh) to view pull requests and retrieve diffs. These are standard read operations for the intended purpose.
- [EXTERNAL_DOWNLOADS]: Pull request data and comments are fetched from GitHub's official API. This targets a well-known service and is necessary for the skill's primary function.
- [PROMPT_INJECTION]: The skill processes external data from PRs, which represents an indirect prompt injection surface. Ingestion points: PR metadata, diffs, and comments are fetched from GitHub (SKILL.md, Step 2). Boundary markers: The instructions do not define specific delimiters for the external content. Capability inventory: The skill is limited to analysis and report generation and does not have access to tools for arbitrary code execution, file modification, or non-GitHub network requests. Sanitization: No specific sanitization or validation of the fetched PR content is mentioned.
Audit Metadata