ui-ux-pro-max

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local script skills/ui-ux-pro-max/scripts/search.py via Python 3 to process design requirements and generate design system recommendations.
  • [COMMAND_EXECUTION]: Documentation provides instructions for environment setup using system package managers (brew, apt, winget), including the use of sudo for Linux distributions, which are standard administrative procedures for installing software prerequisites.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by interpolating user-provided keywords into command-line arguments and subsequently reading the script's output for code generation.
  • Ingestion points: User-supplied strings for product type, industry, and keywords in the search.py command.
  • Boundary markers: The instructions do not define explicit delimiters to encapsulate the script's output when it is returned to the agent.
  • Capability inventory: Execution of local scripts and the ability to create/modify files in the design-system/ subdirectory.
  • Sanitization: No explicit input validation or escaping for the shell arguments is detailed in the markdown documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 06:41 PM
Security Audit — agent-trust-hub — ui-ux-pro-max