azure-aigateway
Warn
Audited by Snyk on Apr 22, 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.md instructions explicitly show importing OpenAPI specs from a public URL (e.g., az apim api import --specification-url "https://raw.githubusercontent.com/...") and instruct importing APIs into APIM/creating MCP tools, meaning the skill ingests open/public third‑party specs that the gateway will parse and which can change exposed tool endpoints and agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata