get-pr-comments
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process review and discussion comments from active pull requests, which constitutes a surface for indirect prompt injection. Malicious actors with access to the pull request could embed instructions within comments to manipulate the agent's summary or prioritize specific tasks.
- Ingestion points: Pull request review and discussion comments (referenced in
SKILL.mdworkflow). - Boundary markers: The workflow lacks specific delimiters or instructions to treat comment content as data rather than instructions.
- Capability inventory: The agent is tasked with resolving the pull request, fetching comments, and generating a prioritized action list.
- Sanitization: No sanitization or validation steps are defined for the fetched external content.
- [NO_CODE]: The skill consists entirely of markdown instructions in
SKILL.mdand does not include any accompanying scripts or executable files.
Audit Metadata