azure-ai-contentsafety-ts

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests untrusted user-generated content (see the moderateContent workflow and calls to client.path("/text:analyze").post with a text parameter and image inputs including blobUrl like "https://storage.blob.core.windows.net/..."), and those analyses directly determine allow/block decisions, so third-party content can materially influence behavior.