langgraph-testing-evaluation

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

• Third-party content exposure detected (high risk: 0.70). The skill's evaluation scripts (e.g., scripts/compare_agents.py/.js and scripts/evaluate_with_langsmith.py/.js) explicitly load datasets from LangSmith via Client.read_dataset / client.list_examples and use those user-provided examples as inputs for agent evaluation, which clearly ingests untrusted, user-generated third-party content that the agent will read and interpret.