openui-forge-openai
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a boilerplate implementation in
app/api/chat/route.tsthat ingests user messages and passes them directly to an LLM backend without boundary markers or sanitization. This represents a standard surface for injection inherent to chat applications. - [EXTERNAL_DOWNLOADS]: The skill references several external packages under the
@openuidevscope and theopenailibrary required for the framework to function. - [COMMAND_EXECUTION]: The documentation includes a command to run a CLI tool using
npx @openuidev/clifor local generation of system prompts from component libraries.
Audit Metadata