ui-design-kit

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input (e.g., "Build me a design system", "UI kit for my project") to generate component code and theme tokens. While this provides a mechanism for processing untrusted data, the skill does not utilize tools with high-privilege capabilities such as arbitrary file writes or network operations, limiting the impact of potential injections.
  • Ingestion points: User design requests in SKILL.md.
  • Boundary markers: None identified.
  • Capability inventory: React component generation, Tailwind configuration, and CSS token generation.
  • Sanitization: Not explicitly implemented for the user-supplied design requirements.
  • [EXTERNAL_DOWNLOADS]: The instructions include logic to delegate theme scaffolding to external tools from the anthropics/skills repository, specifically canvas-design and theme-factory if they are present in the environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 04:19 PM