pencil-design

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No evidence of prompt injection or attempts to bypass agent safety guidelines were detected in the instructions or metadata.
  • [SAFE]: The skill uses platform-specific MCP tools (pencil_, shadcn_) for UI manipulation and component management, which are appropriate for its stated purpose of design-to-code automation.
  • [SAFE]: External references are limited to trusted documentation and official repositories for well-known technologies including Pencil, Tailwind CSS, and shadcn/ui.
  • [SAFE]: No sensitive data access, hardcoded credentials, or unauthorized network operations are present. The skill follows best practices for secret management by recommending the use of environment variables.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 06:00 PM