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 includes a BingGroundingToolDefinition (web search via Bing) that instructs agents to use Bing to answer questions, meaning the agent will fetch and read public web content (untrusted third-party content) as part of its workflow and could be exposed to indirect prompt injection.