azure-ai-vision-imageanalysis-java

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md includes analyzeFromUrl examples (e.g., client.analyzeFromUrl and imageUrl usage) that fetch images from arbitrary public URLs and the READ/OCR feature extracts text from those images, so untrusted third-party content could be ingested and influence analysis or downstream actions.