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.md explicitly shows ingesting external URLs via AnalyzeInput(url="...") (e.g., "Analyze document from URL" examples and the "Use URL sources when possible" guidance), meaning the agent will fetch and interpret arbitrary third‑party web media whose content could contain instructions that influence subsequent behavior.