frontend-design

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains a vast collection of Markdown-based design references. No executable scripts, command lines, or automated network requests are shipped with the skill.
  • [PROMPT_INJECTION]: A static detector flagged a potential concealment pattern in reference/marketing-copywriting.md. However, manual review confirms that the text discusses avoiding 'dark patterns' and instructs the designer not to hide important information (like objections or exit paths) from users. This is defensive guidance for ethical design, not a malicious injection.
  • [EXTERNAL_DOWNLOADS]: The skill mentions and provides installation commands for several well-known and trusted development tools and libraries, including @axe-core/cli, pa11y, and sonner. These are standard industry packages and are presented as recommendations for the developer to use, rather than being executed silently.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 04:03 PM
Security Audit — agent-trust-hub — frontend-design