braintrust-write-eval-scorer
Warn
Audited by Snyk on Aug 20, 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). Required runtime path reads LLM judge input from “span/trace” evidence (which is “text the system under test produced”), so outsider-authored free text can be ingested indirectly if it arrives in user/trace content that the evaluator consumes.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata