verify-ui-auto

Warn

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill instructs the user or agent to run 'npx flutter-skill', which downloads and executes code from the 'ai-dashboard/flutter-skill' repository at runtime.
  • [COMMAND_EXECUTION]: It requires system-level software installation using 'brew install imagemagick' to enable the 'compare' utility.
  • [COMMAND_EXECUTION]: The skill uses shell-based tool chains involving Docker ('docker run') and Flutter CLI ('flutter test') for environment consistency and test execution.
  • [EXTERNAL_DOWNLOADS]: Fetches external resources including Figma screenshots and design context via specific Model Context Protocol (MCP) tools.
  • [EXTERNAL_DOWNLOADS]: Recommends adding several third-party Dart packages from pub.dev such as 'alchemist', 'golden_test', and 'widgetbook_golden_test'.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 1, 2026, 06:02 AM
Security Audit — agent-trust-hub — verify-ui-auto