frontend-design

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external design briefs and user-provided content to generate design plans and UI code. While it lacks explicit delimiters for untrusted content, the instructions focus on aesthetic and layout decisions rather than executing arbitrary logic. The primary capability is text and code generation (CSS/HTML).
  • Ingestion points: The instructions in SKILL.md direct the agent to process user-supplied design briefs and client preferences.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the input data were found.
  • Capability inventory: The skill is designed to generate design tokens, ASCII wireframes, and UI code. SKILL.md mentions a 'write_to_file' pattern in the context of copywriting, which may imply file system interaction for saving UI assets.
  • Sanitization: No sanitization or validation of the external input data is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 10:58 AM