azure-ai-formrecognizer-java

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly shows analyzing documents fetched from arbitrary public URLs (e.g., client.beginAnalyzeDocumentFromUrl with examples like https://example.com/... and the raw.githubusercontent.com sample-invoice.pdf), so the agent ingests untrusted third‑party content as part of its workflow.