generative-ui

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to load visualization libraries such as Chart.js and Mermaid.js from well-known and trusted CDNs including Cloudflare (cdnjs) and esm.sh. These references are standard for web-based data visualization and do not pose a security risk.
  • [COMMAND_EXECUTION]: The skill utilizes a built-in platform tool named show_widget to render HTML and SVG fragments. It also describes a sendPrompt function used for interactive elements within the UI to communicate back to the chat interface, which is an expected part of the described generative UI environment.
  • [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected. The instructions are focused on design principles, color palettes, and layout rules to ensure high-quality, accessible visual output.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 07:39 AM