insights-clustering
Warn
Audited by Snyk on Aug 3, 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). In Steps 2–7 the workflow reads customer/agent free-text fields from ServiceNow tables (e.g.,
incident.description,sn_customerservice_case.description/close_notes,interaction.short_description/close_code/channel, andsys_journal_field.valuefor comments) to perform clustering and sentiment analysis, so outsider-authored text submitted via those records can be ingested at runtime without selecting a specific item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata