visual-polish

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill instructions define qualitative criteria for design audits and do not contain executable code or dangerous system commands. All internal skill references point to related design guidelines within the same vendor scope.- [EXTERNAL_DOWNLOADS]: The skill references technical documentation and design guidelines from well-known services, including Mozilla Developer Network (MDN), Apple's Human Interface Guidelines, and Material Design by Google. These references are used to provide context for UI polish standards.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze UI-related files (e.g., .tsx, .vue, .html, .css). While it lacks explicit boundary markers for these external files, no exploitable capabilities such as network requests, file writes, or dynamic code execution were found within the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 08:26 PM