skills/hktitan/skills/khe-faux-ui/Gen Agent Trust Hub

khe-faux-ui

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation references the installation of companion tools and skills using platform-standard commands like npx skills add. It also notes dependencies on common development packages such as playwright-core, vite, and portless for its UI verification and playground features.
  • [DYNAMIC_EXECUTION]: To verify the visual quality of animated demos, the skill utilizes a headless browser environment (via Playwright) to run generated React components. This "filming" process is an intended functional requirement for capturing frame-by-frame contact sheets and ensuring the accuracy of UI loops.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest project-specific metadata from .design and DESIGN.md files to align its output with the user's design system. While this constitutes a data ingestion surface, the skill uses this information exclusively for styling and design calibration rather than for controlling agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 01:32 PM