code-review
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, providing guidelines, checklists, and examples for high-quality code reviews. It encourages developers to search for security vulnerabilities like SQL injection and XSS.
- [PROMPT_INJECTION]: The skill describes a process for reviewing untrusted code, which is an inherent surface for indirect prompt injection.
- Ingestion points: Source code from Pull Requests or local files processed during reviews.
- Boundary markers: None specified in the skill body to separate instructions from review data.
- Capability inventory: Mentions executing local test runners (e.g., npm test, pytest, cargo test) and using a task_edit tool.
- Sanitization: Not explicitly defined in the provided review instructions.
- [COMMAND_EXECUTION]: The skill references common development commands (e.g., npm test, pytest, cargo test) within an educational context for self-review. These are appropriate for the skill's stated purpose and do not represent a malicious attempt to execute arbitrary code.
- [DATA_EXFILTRATION]: No patterns of unauthorized data access or exfiltration were detected. The skill uses generic placeholders in its code examples.
Audit Metadata