syncfusion-wpf-smart-text-editor

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly registers and consumes responses from external AI providers (Azure OpenAI, OpenAI, Claude, DeepSeek, Gemini, Groq, Ollama) as shown in references/ai-service-configuration.md and references/custom-ai-services.md, and those third-party model outputs are read and used as in-editor suggestions that can change subsequent actions—exposing the agent to untrusted external content that could carry indirect prompt injection.