openui-forge-openai

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install several Node.js dependencies, including standard libraries like openai, zod, and lucide-react, as well as specialized framework packages under the @openuidev namespace. These downloads are consistent with the skill's stated purpose of building a generative UI application.
  • [COMMAND_EXECUTION]: Includes standard development commands for project setup, including npm install for dependency management and npx @openuidev/cli for generating system prompts from local configuration files.
  • [DATA_EXFILTRATION]: Correctly identifies the need for sensitive credentials (OPENAI_API_KEY) and instructs the user to manage them securely using environment variables (.env.local) rather than hardcoding them into the source code.
  • [PROMPT_INJECTION]: The provided backend code processes user messages from a POST request and interpolates them into an LLM prompt. While this defines an attack surface for indirect prompt injection, it is a necessary and standard implementation for the intended chat functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 05:03 PM