open-design

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions are limited to prompt engineering workflows for UI design generation. It does not request access to sensitive file paths, environment variables, or network resources.
  • [EXTERNAL_DOWNLOADS]: The skill references an external repository at 'github.com/nexu-io/open-design' and provides an installation command 'npx skills add nexu-io/open-design'. These are documented as the source for the design system components used by the skill.
  • [PROMPT_INJECTION]: While the skill processes user-provided descriptions to generate UI (Indirect Prompt Injection surface), it is used for the intended purpose of layout generation.
  • Ingestion points: User prompts describing product types and aesthetics (e.g., in SKILL.md under workflows).
  • Boundary markers: None explicitly defined in the provided markdown.
  • Capability inventory: Generation of sandboxed HTML and potential export to PDF/PPTX/MP4.
  • Sanitization: Not specified in the skill instructions; relies on the underlying agent's sandbox and safety layers.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 07:53 PM
Security Audit — agent-trust-hub — open-design