azure-ai-projects-dotnet
Warn
Audited by Snyk on Feb 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill clearly enables agents to perform web searches and ingest public web content—e.g., the "Versioned Agents with Tools (Preview)" example uses ResponseTool.CreateWebSearchTool and the Available Agent Tools lists BingGroundingToolDefinition (web search via Bing), which cause the agent to fetch and read untrusted public web pages/results as part of its workflow.
Audit Metadata