code-quality-review

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to perform code reviews and suggest improvements based on project conventions. All activities described are restricted to analysis and reporting within the provided context.
  • [SAFE]: The instructions explicitly state 'Read-only review. Never edit files or fix anything yourself', which minimizes the risk of unauthorized modifications to the codebase.
  • [SAFE]: The skill uses local repository files (e.g., AGENTS.md, VISION.md, SKILL.md) to gain context. While this is an ingestion surface for potentially untrusted data within a repository, the skill's read-only nature and focused purpose as a reviewer mitigate risks associated with indirect prompt injection.
  • [SAFE]: No obfuscation, hardcoded credentials, remote code downloads, or persistence mechanisms were detected in the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 08:51 PM
Security Audit — agent-trust-hub — code-quality-review