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's examples and APIs (e.g., client.analyzeFromUrl(imageUrl) shown in SKILL.md and references/examples.md, including external URLs like https://example.com/... and raw.githubusercontent.com) explicitly fetch and analyze images from arbitrary public URLs and use the READ (OCR) and captioning features to interpret their content, so it ingests untrusted third-party content that could contain hidden instructions.