code-review-expert
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill operates as a senior engineer persona to review code for architectural smells, performance issues, and security vulnerabilities using provided checklists.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external data in the form of local source code and git diffs (ingestion points in SKILL.md). While it lacks specific delimiters or sanitization for this content, the risk is minimized by a 'review-first' design and a mandatory human-in-the-loop confirmation step before any code is modified (Capability Inventory: Step 7).
- [COMMAND_EXECUTION]: The skill utilizes standard system tools such as
git,rg(ripgrep), andgrepto analyze the project structure and changes. These tools are used appropriately for the skill's stated purpose of inspection and analysis.
Audit Metadata