design-first-ui-prompting

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a set of educational templates and instructions for UI design prompting. It does not contain any executable scripts that interact with the host system, access sensitive files, or perform network operations.
  • [SAFE]: The demo/index.html file contains localized CSS and JavaScript for visual animations and UI state management (e.g., pricing toggles, canvas field animation). The JavaScript code is benign, performs no network requests, and does not use dangerous functions like eval().
  • [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface by instructing the agent to interpolate user-provided goals and copy into a prompt skeleton. However, the structured nature of the template (sections for GOAL, FORMAT, LAYOUT, etc.) and explicit NEGATIVE PROMPT constraints act as effective boundary markers to mitigate accidental instruction leakage.
  • [METADATA_POISONING]: The YAML frontmatter and skill description accurately reflect the technical content provided in the instructions.
  • [EXTERNAL_DOWNLOADS]: The skill references several well-known design industry tools and repositories in REFERENCES.md (Mobbin, Figma, Iconify, Bento Grids, Simple Icons). These are documented for reference purposes and are not automatically downloaded or executed by the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 02:11 AM