ui-ux-pro-max
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (LOW): The documentation contains instructions for users to manually install Python using package managers (apt, brew, winget), which includes 'sudo' commands. These are prerequisites for the user and are not executed automatically by the skill code.
- [DYNAMIC_EXECUTION] (LOW): The search script modifies the Python module search path (sys.path) to include a directory in the user's home folder. This is used to load a local utility script for character encoding compatibility.
- [DATA_EXFILTRATION] (SAFE): No network operations (e.g., requests, sockets, curl) were found in the Python scripts. Data access is restricted to the local 'data' directory within the skill folder.
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill reads from local CSV data files which are then displayed to the agent. (1) Ingestion points: CSV files in 'data/' directory. (2) Boundary markers: Search results are formatted into Markdown lists with '### Result' headers. (3) Capability inventory: The skill provides UI/UX advice; the agent uses this advice to generate frontend code. (4) Sanitization: The core search logic tokenizes queries to remove most non-alphanumeric characters and truncates result strings to 300 characters.
Audit Metadata