openai-ui-skills
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of static markdown documentation and a JSON metadata file defining design constraints (colors, typography, spacing). It does not contain scripts, command execution, or network operations.
- [METADATA_POISONING]: The skill correctly attributes its source to a trusted organization (OpenAI). While it includes claims about being safe or having opinionated constraints, these are consistent with its documented purpose as a UI design system reference.
Audit Metadata