document-extraction

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

• Third-party content exposure detected (medium risk: 0.30). Outsider-authored text can be ingested at runtime indirectly via documents/attachments provided by the workflow user (e.g., uploaded PDFs/images referenced by sn_doc_intelligence_extraction.source_document) and then processed into sn_doc_intelligence_extraction_result for review/mapping.