final-review
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates in a read-only capacity regarding product code and test suites, explicitly stating that it never edits code, commits changes, or mutates trackers.
- [DATA_EXPOSURE]: The skill reads project documentation and Git diffs to perform its review. This is standard behavior for a code review agent and does not involve accessing sensitive system files or credentials.
- [COMMAND_EXECUTION]: The skill utilizes standard Git commands (
git diff) and file system reads/writes within the scope of the project's documentation and run artifacts. It does not spawn shells or execute untrusted inputs. - [INDIRECT_PROMPT_INJECTION]: While the skill processes untrusted data (Git diffs and project documentation) which could contain malicious instructions, the risk is mitigated by its design as a non-executing drafting tool that outputs only Markdown artifacts for orchestrator/human review.
Audit Metadata