arize-prompts
Warn
Audited by Snyk on Sep 11, 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 skill workflow involves exporting LLM traces (
ax spans export) from an Arize project, which can ingest outsider-authored prompt text and span inputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata