find-traces
Warn
Audited by Snyk on Oct 13, 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 instructs the agent to read user traces, annotations, and trace attributes using the
langwatch trace getcommand, which ingests outsider-submitted free text from user-generated traces and interactions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata