local-review
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill utilizes standard developer utilities (git, gh) to perform expected repository maintenance and review tasks.\n- [PROMPT_INJECTION]: The skill ingests and processes untrusted data from pull request diffs and metadata, creating a surface for indirect prompt injection.\n
- Ingestion points: Data enters the context via
git diff,gh pr diff,gh pr view, and root/localCLAUDE.mdfiles.\n - Boundary markers: No markers or warnings are used to distinguish untrusted data from the skill's instructions.\n
- Capability inventory: The skill can read local source code and post comments to GitHub pull requests.\n
- Sanitization: No input validation or content filtering is performed on the ingested PR data.
Audit Metadata