Build UIs with @nuxt/ui v4 — 125+ accessible Vue components with Tailwind CSS theming. Use when creating interfaces, customizing themes to match a brand, building forms, or composing layouts like dashboards, docs sites, and chat interfaces.
72
89%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The skill’s required runtime workflow enables a chat UI that ingests outsider-authored free text via user input (`input`) and sends it to the server (`sendMessage({ text: input.value })` / `readBody(event)` → `convertToModelMessages(messages)`), so the LLM sees attacker-controlled text without first selecting a specific trusted item.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The skill config adds and instructs the agent to use the Nuxt UI MCP server at https://ui.nuxt.com/mcp, which will be called at runtime to fetch component API/docs that directly influence prompts and agent behavior.
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.