debug-with-langwatch

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

• Third-party content exposure detected (medium risk: 0.30). At runtime, the workflow uses LangWatch CLI commands like langwatch trace search and langwatch trace get to ingest and inspect stored trace span inputs/prompts that may contain outsider-authored text (e.g., user messages and error strings) without selecting a specific safe item.