frontend-mix-design

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-supplied planning documents to generate frontend code, which introduces a surface for indirect prompt injection.
  • Ingestion points: The skill reads an external file path provided in the $ARGUMENTS variable using the Read tool.
  • Boundary markers: Instructions explicitly direct the agent to only extract content from the `## SECTION A
  • UI Scope` header and ignore other sections, providing a structural delimiter.
  • Capability inventory: The skill allows the agent to create directories and write frontend code files (Next.js components, summary reports) to the local filesystem.
  • Sanitization: No specific content sanitization or escaping is mentioned, but the skill includes explicit constraints against performing network calls, installing auth SDKs, or creating server-side routes.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 11:39 PM
Security Audit — agent-trust-hub — frontend-mix-design