syncfusion-angular-ai-assistview

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

• Third-party content exposure detected (high risk: 0.90). The skill's AI integration guide (references/ai-integrations.md) includes runtime fetches to external/public AI endpoints (Azure OpenAI, Gemini, Lite‑LLM, Ollama, streaming endpoints) whose responses are ingested, rendered (references/assist-view-basics.md: markdown/streaming) and used in event handlers to update the UI and switch views (references/custom-views.md), meaning untrusted third‑party content can directly influence agent behavior beyond mere display.