langsmith-code-eval

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

• Third-party content exposure detected (high risk: 0.90). The skill's inspection scripts (scripts/inspect_dataset.py and scripts/inspect_trace.py) use langsmith.Client (client.read_dataset, client.list_examples, client.list_runs, client.read_run) to fetch and print/analyze dataset examples, example.metadata, and run.outputs/messages from the LangSmith service, so the agent will ingest and interpret untrusted user-provided dataset/trace content.