visual-consistency

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's configuration and metadata (YAML frontmatter) are consistent with its purpose as a design review tool. The capability manifest correctly indicates no network, shell, or filesystem write permissions are required by the skill itself.
  • [SAFE]: No obfuscation techniques, such as Base64-encoded commands, zero-width characters, or homoglyphs, were detected in any of the files.
  • [SAFE]: All external URLs and resources point to established documentation, design systems, and well-known industry blogs (e.g., MDN, Google's web.dev, CSS-Tricks, and official design systems like Carbon or Polaris). These represent safe, authoritative references.
  • [SAFE]: While the skill defines a workflow for the agent to review external code (an indirect prompt injection surface), it includes severity levels and autonomy guards (Judgment vs Safe) that emphasize human-in-the-loop for non-obvious changes, which is a standard safety practice for code analysis tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:50 AM
Security Audit — agent-trust-hub — visual-consistency