analysis-methods
Warn
Audited by Snyk on Jul 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required workflow only ingests runtime-readable text from the SMART FHIR server via
fhir_get()/get_all_pages()(e.g.,Condition,Observation,MedicationRequestresources), which are not authored by the operating user; this JSON is parsed and then used to build the analysis context (e.g., lab values/med names).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata