light-review-existing-diffs
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill contains only natural language instructions for code review tasks and does not include any scripts, executable commands, or network activity.
- [INDIRECT_PROMPT_INJECTION]: The skill involves processing untrusted code diffs, which is a potential surface for indirect prompt injection. Ingestion points: git diffs and pending commits (SKILL.md). Boundary markers: None. Capability inventory: No tool usage or script execution is enabled (model invocation is disabled). Sanitization: None. The risk is negligible as there are no executable tools for an injection to target.
Audit Metadata