langchain-agent-tracing
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 verification workflow lists and reads full production traces (
langsmith traces list --last-n-minutes 30andtraces get --full, plus reading real trace inputs and outputs at lines 148 and 185-195), and those traces record end-user input that outsiders can submit to the application without the agent selecting a specific item.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill documents state-changing operations on a shared LangSmith workspace, including registering an agent with
langsmith agents createand removing legacy tracing variables from deployment runtimes, but it establishes no explicit irreversible operational loss, so it stays at low.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata