azure-ai-contentunderstanding-py

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly ingests and analyzes arbitrary URLs via AnalyzeInput(url="...") / client.begin_analyze (e.g., "https://example.com/document.pdf", images, audio, video), meaning it fetches and interprets untrusted public third‑party content from the open web.