langchain-eval-engineering
Warn
Audited by Snyk on Nov 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 required workflow reads production trace threads (LangSmith via
runs list/threads list/threads get) whenever the user supplies traces, and those threads contain end-user messages that an outside party can generate by using the deployed agent, so the agent ingests outsider-authored text without first selecting a specific item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata