medical-entity-extractor
Warn
Audited by Snyk on Jul 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow ingests user-provided message content via the
inputJSONbodyfield (unstructured patient messages) to perform medical entity extraction, so outsider-authored free text is directly read by the LLM at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata