agent-framework-azure-ai-py

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly includes and uses HostedWebSearchTool (Bing) in examples (e.g., "HostedWebSearchTool(name='Bing')" and the "Search for Python best practices and summarize" flow), meaning the agent will fetch and read public web pages/search results which are untrusted third‑party content that could contain instructions affecting agent behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The example creates an MCPStreamableHTTPTool with the URL "https://learn.microsoft.com/api/mcp", which is used at runtime and likely fetches streaming MCP content that can directly drive agent instructions/behavior.