ui-ux-pro-max

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent or user to install Python using official system package managers (brew, apt, winget) if it is not already present. This includes a command for sudo apt install python3.
  • [COMMAND_EXECUTION]: The skill relies on the execution of a local Python script (skills/ui-ux-pro-max/scripts/search.py) to process user queries and retrieve design guidelines. The script is invoked with user-supplied arguments to filter design domains.
  • [DATA_EXPOSURE]: The skill features a persistence mechanism (--persist) that writes design system configurations and page-specific overrides to the local file system in the design-system/ directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input (product types, industries, keywords) via CLI arguments which are then used to influence the agent's design decisions.
  • Ingestion points: User-supplied strings passed to search.py as query arguments.
  • Boundary markers: None explicitly defined in the instructional text.
  • Capability inventory: Local script execution (python3), file writing (design-system/MASTER.md).
  • Sanitization: The skill instructions do not specify how the Python script handles or escapes the user-provided keywords before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 05:22 PM
Security Audit — agent-trust-hub — ui-ux-pro-max