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.md explicitly shows creating a BingGroundingToolDefinition and an agent with instructions "Use Bing to answer questions about current events" (see section "7. Bing Grounding"), which means the agent will fetch and interpret open/public web search results (untrusted third-party content) that can materially influence its actions.