azure-ai-projects-py

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly includes web‑grounding and web search tools (e.g., BingGroundingTool / WebSearchTool "Use web search to find current information") and file-search/RAG tools that let agents fetch and ingest public web pages and user-uploaded documents (untrusted third‑party content) which the agent is expected to read and interpret as part of runs.