azure-ai-contentunderstanding-py

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md shows core workflows that call begin_analyze with AnalyzeInput(url="...") (e.g., "Analyze document from URL" and the "Use URL sources" best practice), so the agent fetches and processes arbitrary public URLs whose untrusted content can influence analysis and downstream actions.