frontend-design
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install components and design systems from well-known and trusted organizations, including Microsoft (Fluent UI), IBM (Carbon), GitHub (Primer), and others. It also utilizes assets from well-known services like Simple Icons and Picsum Photos for placeholders.
- [INDIRECT_PROMPT_INJECTION]: The included diagnostic tools (
scripts/ux_audit.pyandscripts/accessibility_checker.py) read and analyze local project files (.html,.jsx,.tsx, etc.) to provide feedback to the agent. While this creates a surface where external file content enters the agent's context, the scripts are restricted to local static analysis and do not execute or interpret the code they read. - Ingestion points: The audit scripts use
rglobto read all HTML, JSX, and TSX files in the project directory. - Boundary markers: Absent; the scripts provide raw or summarized findings to the agent based on regex matches.
- Capability inventory: The skill is configured with tool permissions for
Read,Write,Edit,Glob,Grep, andBashexecution. - Sanitization: The scripts use regex for pattern matching and do not perform active sanitization of the file content before scanning.
Audit Metadata