azure-ai-contentsafety-py

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

• Third-party content exposure detected (high risk: 0.90). This skill accepts arbitrary external media via Analyze Image's ImageData.blob_url (see "Image from URL" example with "https://example.com/image.jpg"), meaning the agent would fetch and analyze untrusted public content (images) as part of its workflow and could be exposed to indirect prompt injection.