azure-ai-translation-document-py

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the azure-ai-translation-document package, which is an official library provided by Microsoft.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8) due to its document processing nature.
  • Ingestion points: The skill reads external documents from Azure Blob Storage containers (via AZURE_SOURCE_CONTAINER_URL) and local file paths (e.g., document.docx) to perform translation.
  • Boundary markers: There are no explicit delimiters or instructions provided to the model to ignore potential instructions embedded within the source documents.
  • Capability inventory: The skill performs network requests to Azure AI services and has the capability to write translated content to local files (e.g., document_es.docx) or remote storage containers.
  • Sanitization: No content validation or sanitization of the documents being translated is described in the implementation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:37 PM