arize-prompts
Warn
Audited by Snyk on Sep 10, 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 allows exporting span data (
ax spans export) from an Arize project, which may contain outsider-authored free text from LLM inputs/prompts that the agent ingests into context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata