agent-framework-azure-ai-py

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

• Third-party content exposure detected (high risk: 0.85). The required workflow includes HostedWebSearchTool (Bing) and/or MCPStreamableHTTPTool with a runtime URL; these tools fetch external web/MCP content and feed the retrieved page/text into the agent’s LLM context, which is outsider-authored free text.