arize-prompt-optimization
Warn
Audited by Snyk on Sep 15, 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 workflow reads production traces, annotations, evaluation explanations, and dataset/experiment inputs/outputs from Arize via the ax CLI, which can contain outsider-authored free text from end-user inputs to the monitored application.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata