azure-ai-contentsafety-java

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md includes an "Analyze Image from URL" example that calls AnalyzeImage with ContentSafetyImageData.setBlobUrl("https://example.com/image.jpg"), showing the agent can fetch and analyze arbitrary external image URLs (untrusted third-party content) as part of its workflow.