fe-codegen-workbench

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: Uses standard package managers to initialize projects and install dependencies (e.g., pnpm dlx create-admin-platform, npm create vite, and npm install). These operations are necessary for the skill's primary function of scaffolding new frontend applications.
  • [EXTERNAL_DOWNLOADS]: Fetches design system configuration data and tokens from https://getdesign.md/ to support themed code generation. These network operations are limited to design specifications and do not involve sensitive data.
  • [SAFE]: Integrates with trusted external skills from organizations such as Vercel and Anthropic for code review and design best practices, following established security guidelines for dependency management.
  • [SAFE]: Includes environment-specific development artifacts, such as MCP configuration in .cursor/mcp.json, which appear to be remnants from the author's local setup but do not present a security risk to end users.
  • [SAFE]: While the skill manages high-privilege capabilities including file system writes and shell execution, its operations are strictly confined to the project development lifecycle as defined in its instructional flow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 09:31 AM
Security Audit — agent-trust-hub — fe-codegen-workbench