azure-ai-document-intelligence-ts

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts arbitrary public URLs as inputs (see "Analyze Document (URL)" and examples like "Extract Invoice Fields", "Extract Receipt Fields", and "Classify Document" which use body: { urlSource: ... } / documentUrl), so the agent will fetch and interpret untrusted third-party documents that could influence its actions.