azure-aigateway

Warn

Audited by Snyk on Feb 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). The skill explicitly imports OpenAPI specs from public URLs ("Pattern 9: Import API from Web URL" showing az apim api import --specification-url ...) and converts APIs into MCP tools/endpoints (Pattern 10's MCP tools/list), meaning it fetches and ingests untrusted public API specs which can be interpreted as tool definitions and thus could indirectly inject instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 03:33 AM