skill-reviewer
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFE
Full Analysis
- [Structured Data Processing]: The skill is designed to analyze external content (skill definitions in Pull Requests), which enters the agent context through the collection of changed files. This represents a standard surface for indirect prompt injection; however, the skill effectively manages this by using a highly structured, checklist-driven evaluation process that keeps the agent focused on technical compliance.
- [Development Workflow Integration]: The instructions include references to standard local development commands such as
npm testandnpm run tokens. These are used specifically for validating skill registration and performance, which is expected behavior for a code-review tool operating within a managed development environment.
Audit Metadata