omero-integration

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

• Third-party content exposure detected (medium risk: 0.30). Skill runtime uses the OMERO Python API to retrieve user-controlled object text such as Image descriptions, annotation textValues/comments, and ROI shape labels via calls like getDescription()/listAnnotations()/shape.getTextValue(), which are outsider-authored and then ingested by the LLM as free text if the host feeds them into the model.