skills/uinaf/design/uinaf-design/Gen Agent Trust Hub

uinaf-design

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill facilitates interaction with official design resources provided by the author and utilizes local project scripts for validation without introducing malicious patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from external vendor-owned URLs (design.uinaf.dev), which represents a standard design system integration surface.
  • Ingestion points: Data retrieved from https://design.uinaf.dev/mcp and https://design.uinaf.dev/llms.txt (SKILL.md).
  • Boundary markers: None present.
  • Capability inventory: Fetches network content and executes local project scripts via npm run design:check (SKILL.md).
  • Sanitization: Not explicitly implemented within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 01:06 PM
Security Audit — agent-trust-hub — uinaf-design