engineering-code-review

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill contains no executable code, persistence mechanisms, or privilege escalation patterns. It functions as a set of behavioral guidelines for the AI agent to follow during code analysis.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation from Google's engineering practices hosted on GitHub Pages. These are informational links to a well-known service used for educational context.
  • [PROMPT_INJECTION]: The skill involves reviewing external code, pull requests, and descriptions, which constitutes a surface for indirect prompt injection. The instructions mitigate this by providing a structured checklist and requiring technical facts and data for verdicts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 01:17 AM
Security Audit — agent-trust-hub — engineering-code-review