nuxt-ui
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to configure an external MCP server at
https://ui.nuxt.com/mcp. This server provides the AI agent with real-time access to component documentation, props, and examples for the Nuxt UI library. - [INDIRECT_PROMPT_INJECTION]: The
references/layouts/chat.mdfile provides patterns for building AI chat interfaces, which naturally ingest untrusted data from external sources and streaming LLM responses. - Ingestion points: Data enters the application context via the
readBody(event)function in the server-side API handler and theuseChatcomposable in the client-side Vue files. - Boundary markers: Content is rendered using the
Comarkcomponent, which properly segregates markdown tokens and facilitates the use of Nuxt UI prose components. - Capability inventory: The provided chat patterns include support for tool calls (
isToolUIPart), which the agent can use to perform actions based on model instructions. - Sanitization: Content rendering relies on the
Comarklibrary for markdown parsing and standard Nuxt UI components for structured data display, following industry-standard safety practices for AI-enabled UIs. - [SAFE]: All suggested dependencies and remote resources originate from well-known technology providers or the official project documentation site associated with the skill's primary purpose.
Audit Metadata