cohort-compare
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 workflow queries FHIR endpoints at runtime (e.g.,
GET /Condition?...and batchedGET /Observation?.../GET /MedicationRequest?...via thecurlhelper), and the returned resources’ free-text fields (e.g., medication names, labvalueString, etc.) are ingested into the agent’s LLM context as readable text—these are outsider-authored clinical data from external systems.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata