omero-integration

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to connect to external OMERO servers and programmatically retrieve and read user-provided content (images, Map/File/Comment annotations, files) via calls like conn.getObject, image.listAnnotations, metadataService.loadSpecifiedAnnotations and raw file downloads (see references/data_access.md and references/metadata.md), and that untrusted content is used in workflows and scripts to drive analysis or processing decisions.