azure-ai-projects-java

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

• Third-party content exposure detected (high risk: 0.90). The skill's examples and core operations (SKILL.md and references/examples.md) show using FileDatasetVersion.setDataUri and datasetsClient.createOrUpdateVersion with arbitrary HTTPS URLs (e.g., setDataUri("https://example.com/data.txt")), which indicates the SDK can ingest content from external public URLs that could contain untrusted, user-provided instructions influencing downstream operations.