ui-ux-pro-max

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely locally using Python's standard library to search and retrieve UI/UX design data from bundled CSV files.
  • [COMMAND_EXECUTION]: The skill instructions in SKILL.md recommend standard environment setup commands for the user (e.g., brew install, apt install, winget install) to ensure Python is available. These are documented for the user and are not executed autonomously by the agent in a hidden or malicious manner.
  • [DATA_EXPOSURE_EXFILTRATION]: No network-capable modules (like requests or urllib) or exfiltration patterns were found. File access is strictly limited to the skill's own data directory using relative path calculations in scripts/core.py.
  • [PROMPT_INJECTION]: While the skill contains a prompts.csv file with AI-oriented keywords, these are intended as design templates for the agent to assist with UI generation and do not contain instructions to bypass safety filters or ignore system prompts.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes internal CSV data. While it lacks explicit boundary markers when returning search results to the agent, the data sources are static, local files provided within the skill package, significantly limiting the risk of external data poisoning.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 01:44 PM