braintrust-discover-trace-topics
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). The skill’s required runtime workflow ingests free-form, user- and model-generated trace content via a configured/“thread” preprocessor (“thread returns the LLM messages per span”) and then runs the facet on that preprocessed text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata