skills/mengto/skills/gpt-taste/Gen Agent Trust Hub

gpt-taste

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or persistence mechanisms were detected in the instructions. The skill focuses entirely on design engineering and UI code generation.- [EXTERNAL_DOWNLOADS]: The skill references well-known and trusted external services for placeholder images (picsum.photos) and icon libraries (@phosphor-icons/react) common in professional frontend development.- [COMMAND_EXECUTION]: Instructions to simulate a Python script are used as a prompting technique to ensure the AI generates varied, deterministic random choices for layout options in its text output, rather than requesting actual system-level execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 08:34 AM
Security Audit — agent-trust-hub — gpt-taste