skills/matematicsolutions/awesome-matematic-skills-pl/matematic-patron-pr-review-pl/Gen Agent Trust Hub
matematic-patron-pr-review-pl
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data in the form of code diffs and repository metadata. A malicious PR or code change could contain instructions designed to influence the agent's behavior during the review process.\n
- Ingestion points: Code diffs and PR metadata are fetched from the repository using
gh pr diff,gh pr view, andgit diffas described in the review workflow.\n - Boundary markers: The skill lacks explicit delimiters or instructions to treat the diff content strictly as data, which increases the possibility of the agent accidentally executing instructions embedded within the code.\n
- Capability inventory: The skill has access to the
Bashtool, which it uses to runrg(ripgrep),git grep, and the GitHub CLI (gh).\n - Sanitization: No documented mechanisms for sanitizing or escaping external content before interpolation into the agent's context were found.
Audit Metadata