openui-forge-langchain
Pass
Audited by Gen Agent Trust Hub on May 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of several Node.js packages, including vendor-scoped packages such as @openuidev/react-ui, @openuidev/react-headless, and @openuidev/react-lang.
- [COMMAND_EXECUTION]: Provides instructions to execute a CLI tool via
npx @openuidev/clifor generating system prompts, which is a standard part of the library's integration workflow. - [PROMPT_INJECTION]: The skill implements a chat backend that processes user messages and passes them to an LLM, creating an indirect prompt injection surface.
- Ingestion points: User messages are ingested via the
POSTrequest body inapp/api/chat/route.ts. - Boundary markers: None identified; messages are mapped directly to LangChain message classes (
HumanMessageandAIMessage). - Capability inventory: The skill facilitates streaming LLM output to a frontend UI and allows defining custom React components via the
@openuidev/react-langlibrary. - Sanitization: No explicit sanitization, validation, or filtering of the user-provided message content is implemented in the provided backend code snippets.
Audit Metadata