langsmith-trace

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill's scripts (scripts/query_traces.py) call langsmith.Client.list_runs to fetch traces from the LangSmith service and can include run "inputs" and "outputs" (via --include-io/--full), which may contain arbitrary/untrusted user-generated or third-party content that the agent will read and display.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 03:14 AM