award-design

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references established GitHub repositories from organizations like Google and Vercel. It recommends using standard packages such as @google/design.md for linting, which are part of a well-known development ecosystem.
  • [COMMAND_EXECUTION]: It suggests using the npx command to run design linting tools and optionally utilizes visual audit tools like dev-browser. These tools are used for their intended purpose of verifying design quality and consistency in a development environment.
  • [PROMPT_INJECTION]: The instructions include 'Axiomatic rejections' and 'Hard rules' that serve as heuristics to improve the quality of the AI's design output. These are internal project constraints rather than attempts to bypass the agent's safety or ethical guidelines.
  • [SAFE]: The skill provides extensive documentation on production hardening, performance targets, and accessibility standards, demonstrating a focus on best practices in web software engineering.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 09:29 AM