designing-systems

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill consists of markdown documentation and design reference files. It does not include executable scripts, shell commands, or obfuscated logic.
  • [EXTERNAL_DOWNLOADS]: The typography configuration in references/typography.md references CSS font imports from Fontshare (api.fontshare.com). This is a well-known typography service and the usage is appropriate for the skill's purpose.
  • [PROMPT_INJECTION]: The skill's workflow involves analyzing existing codebase files to extract design tokens using the fuse-ai-pilot:explore-codebase tool. While this creates an ingestion point for indirect prompt injection from untrusted codebase content, the risk is negligible as it is restricted to design-related tasks. \n
  • Ingestion points: Existing CSS variables and Tailwind configurations in the user codebase. \n
  • Boundary markers: Not specified. \n
  • Capability inventory: Read, Write, Edit, Glob, Grep, Task. \n
  • Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 02:51 AM
Security Audit — agent-trust-hub — designing-systems