check-pr
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources that could contain hidden instructions targeting the agent.
- Ingestion points: Reads pull request descriptions, inline review comments, and general discussion notes from GitHub, GitLab, and Perforce platforms (SKILL.md, references/gitlab-api.md, references/graphql-queries.md).
- Boundary markers: The instructions do not include requirements for the agent to use delimiters or ignore embedded instructions when reading these external fields.
- Capability inventory: The skill has significant write permissions, including the ability to commit and push code (
git push), re-shelve Perforce changelists (p4 shelve), and resolve review threads or discussions via API (SKILL.md). - Sanitization: No sanitization, filtering, or validation logic is specified for the ingested PR/MR/CL content before processing.
Audit Metadata