azure-ai-agents-persistent-dotnet

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly creates agents with a Bing Grounding tool ("7. Bing Grounding") that directs the agent to use Bing web search to answer questions, so the agent will fetch and interpret public/untrusted web content that can materially influence its actions.