LangSmith Datasets

Warn

Audited by Snyk on Feb 24, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). This skill explicitly ingests external, user-provided trace files and remote LangSmith datasets (via Client.read_dataset / list_examples and the CLI commands shown in SKILL.md and query_datasets.py/ts), parsing their inputs/outputs and using that content to generate/upload datasets—so untrusted third-party content is read and can influence subsequent processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 24, 2026, 07:38 AM