arize-prompts
Warn
Audited by Snyk on Jul 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). Workflow B explicitly ingests exported LLM span text (untrusted/outsider-authored user content) from
ax spans export/ reconstructed messages into the assistant’s own prompt context before issuingax prompts create/create-version, creating an indirect prompt-injection risk.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata