azure-ai-contentunderstanding-py

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly shows using AnalyzeInput(url="https://...") (see "Analyze document from URL" examples and the Best Practices note "Use URL sources when possible"), meaning the client fetches and analyzes arbitrary public URLs (documents, images, audio, video), which exposes the agent to untrusted third‑party content that could contain instructions.