azure-ai-projects-dotnet
Warn
Audited by Snyk on Mar 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The "Versioned Agents with Tools (Preview)" workflow and the Available Agent Tools listing (e.g., ResponseTool.CreateWebSearchTool / "Bing Grounding") show the agent can perform web searches and ingest public web results, meaning it will fetch and interpret untrusted third‑party content that can influence its actions.
Audit Metadata