skills/fpasquet/skills/design-system/Gen Agent Trust Hub

design-system

Pass

Audited by Gen Agent Trust Hub on Nov 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local Node.js scripts included in the package (such as audit.mjs, scaffold.mjs, and rehome.mjs) to automate design system tasks. These scripts perform necessary file system operations including reading source code and writing refactored files.
  • [EXTERNAL_DOWNLOADS]: The skill's templates and documentation recommend the installation of standard, well-known development dependencies from the official NPM registry, including tailwindcss, storybook, and radix-ui. These are well-known services and do not pose a security risk in this context.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process local source code files, which represents an attack surface for indirect prompt injection.
  • Ingestion points: Local React components and CSS files are read and analyzed by the provided auditing and refactoring scripts.
  • Boundary markers: No explicit markers are used to separate ingested code from agent instructions.
  • Capability inventory: The skill possesses capabilities for reading and writing files and directory manipulation within the user's project.
  • Sanitization: The scripts use structural parsing and regex for code transformation; they do not execute the content of the files they process.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 8, 2026, 03:50 PM