audit-uiux-design-system

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates a vulnerability surface for indirect prompt injection due to its reliance on external data sources for design research.
  • Ingestion points: External web content is ingested via the firecrawl:firecrawl_search tool in Step 1 to retrieve design system standards and award-winning reference sites.
  • Boundary markers: The instructions lack explicit boundary markers or delimiters to isolate untrusted web content from the agent's core logic.
  • Capability inventory: The skill possesses capabilities for shell command execution (via Playwright) and extensive file system traversal/reading (via Glob and Grep).
  • Sanitization: There are no defined procedures to sanitize, filter, or validate the external search results before they are used to influence the audit report or subsequent agent actions.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx --yes @playwright/cli@latest to download and execute the Playwright CLI at runtime. This download targets the official NPM registry for a well-known developer tool provided by a reputable service.
  • [COMMAND_EXECUTION]: The skill executes shell commands to automate browser-based visual verification using Playwright. This includes opening local URLs, taking snapshots, and capturing screenshots to document UI consistency issues.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 11:26 PM