azure-ai-projects-dotnet
Warn
Audited by Snyk on Apr 21, 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). This skill's "Versioned Agents with Tools (Preview)" workflow shows creating agents with a web-search tool (ResponseTool.CreateWebSearchTool / Bing Grounding) which fetches and feeds public web content into the agent's responses, allowing untrusted third-party pages to influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata