azure-architecture
Warn
Audited by Snyk on Apr 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires runtime fetching of external Markdown from Microsoft Learn (e.g., https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/azure-openai-gateway-custom-authentication), which the agent will inject into its context via the mcp_microsoftdocs or fetch_webpage tool and thus can directly control prompts/content used at runtime.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata