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.pyvia 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 ofsudofor 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.pycommand. - 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