azure-ai-agents-persistent-dotnet

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

• Third-party content exposure detected (high risk: 0.95). The runtime workflow ingests OUTSIDER-authored free text via the user-provided message body passed to client.Messages.CreateMessageAsync(thread.Id, MessageRole.User, "..."), which becomes part of the agent’s thread context that the LLM reads during CreateRunAsync/streaming.