windmill

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

• Third-party content exposure detected (high risk: 0.80). The skill includes scripts that fetch and process arbitrary external data (e.g., scripts/data_processing/fetch_and_transform.py uses a user-supplied api_endpoint to GET and parse JSON, and webhook_handler.ts processes incoming webhook payloads), so the agent will read and interpret untrusted third-party content.