ha-pr-comment-audit
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes content from GitHub pull request review comments. Because this data comes from external contributors, it could potentially contain instructions designed to influence the agent (indirect prompt injection). * Ingestion points: External GitHub review comments fetched via the GitHub API (gh api). * Boundary markers: The instructions do not specify any delimiters or safety markers to isolate the untrusted comment text from the agent's system instructions. * Capability inventory: The skill utilizes the GitHub CLI (gh) to read pull request data and API responses. * Sanitization: The skill does not define methods for sanitizing, escaping, or validating the content of the comments before processing.
Audit Metadata