predictive-intelligence
Warn
Audited by Snyk on Aug 9, 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). SKILL.md describes an ES5 ServiceNow PI workflow that ingests text from ServiceNow records at runtime (e.g., calling
sn_ml.ClassificationPredictor.predict(gr)orpredict(current)using fields likeshort_description/description), where outsider-authored incident/case content can be present in those records.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata