braintrust-build-eval-dataset
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). At runtime, this skill builds/audits eval datasets by sampling and reading “production traces” and other sourced items, where trace/dataset row text may contain user turns or system-like instruction content that the LLM ingests as evidence.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata