contributions-rank
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external GitHub issue comments which could potentially contain instructions to manipulate the ranking outcome.
- Ingestion points: Comments on scout sub-issues are read via multica and gh CLI tools.
- Boundary markers: Untrusted data from sub-issues is not isolated using specific delimiters or safety instructions.
- Capability inventory: The skill can read repository metadata and post comments to issues, but it cannot modify code or open pull requests.
- Sanitization: No explicit sanitization or validation of the ingested comments is performed.
- [EXTERNAL_DOWNLOADS]: Fetches a scoring rubric from the author's own mmontes11/contributions repository on GitHub. This is documented as the single source of truth for the workflow and represents normal vendor functionality.
Audit Metadata