ui-ux-pro-max

Warn

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the execution of a local Python search utility (skills/ui-ux-pro-max/scripts/search.py) using user-supplied queries to generate design recommendations.
  • [COMMAND_EXECUTION]: The instructions include system commands requiring elevated privileges (sudo apt update && sudo apt install python3) to install dependencies if they are missing from the environment.
  • [PROMPT_INJECTION]: An indirect prompt injection surface exists in the persistence workflow where search results are saved to design-system/MASTER.md via the --persist flag. 1. Ingestion points: User-provided query parameters passed to the search script. 2. Boundary markers: Absent in the generated Markdown files. 3. Capability inventory: File system write access via the search script and read access via instructions to the agent. 4. Sanitization: No evidence of input validation or output escaping for the persisted design system rules.
  • [EXTERNAL_DOWNLOADS]: The skill references downloading software from well-known package managers including Homebrew, APT, and Winget to satisfy Python environment requirements.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 3, 2026, 08:42 AM
Security Audit — agent-trust-hub — ui-ux-pro-max