azure-ai-anomalydetector-java

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

• Third-party content exposure detected (high risk: 0.70). The skill's required examples and workflow explicitly instruct ingesting data from arbitrary Azure Blob Storage URLs (e.g., ModelInfo.setDataSource and MultivariateBatchDetectionOptions.setDataSource using https://storage.blob.core.windows.net/...?sasToken shown in SKILL.md and examples), so the agent will fetch and act on untrusted external data that can materially influence training and inference.