get-pr-comments
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize external, untrusted data in the form of pull request review and discussion comments.
- Ingestion points: Pull request review comments and discussion comments are fetched in
SKILL.md(Workflow steps 1 and 2). - Boundary markers: The instructions do not define any delimiters or system-level warnings to distinguish between the agent's instructions and the content of the comments being processed.
- Capability inventory: The skill identifies and summarizes feedback to create an action list, which could be influenced by malicious content within a PR comment (e.g., instructions to ignore specific bugs or highlight non-existent issues).
- Sanitization: No sanitization, filtering, or validation steps are defined for the incoming comment text.
Audit Metadata