creative-tim-ui

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's install and registry workflow explicitly fetches and ingests block JSON from the public Creative Tim site (e.g., https://www.creative-tim.com/ui/r/.json and https://www.creative-tim.com/ui/llms.txt), so the agent consumes third‑party web content that can directly influence installs and code-generation actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs runtime installs that fetch and execute remote code (via npx @creative-tim/ui and npx shadcn@latest which pull block JSON from URLs like https://www.creative-tim.com/ui/r/.json and the registry at https://www.creative-tim.com/ui), so these external URLs are required at runtime and can deliver executable content into the environment.