frontend-design

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python and Node.js scripts to perform its functions. Specifically, it calls python3 skills/ui-ux-pro-max/scripts/search.py and node .claude/skills/brand/scripts/inject-brand-context.cjs. These scripts appear to be internal components of the vendor's skill ecosystem.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) by interpolating untrusted user input directly into shell command arguments.
  • Ingestion points: User-provided strings for product type, industry, and keywords within the design brief.
  • Boundary markers: Absent; the inputs are placed directly into a shell command template.
  • Capability inventory: Subprocess execution of Python scripts via the shell.
  • Sanitization: The skill instructions do not specify any validation or escaping for the user-provided parameters before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 11:43 PM
Security Audit — agent-trust-hub — frontend-design