message_queues

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

• Third-party content exposure detected (high risk: 0.80). The skill includes examples that fetch and process arbitrary external URLs—e.g., the Celery example process_image(image_url) and the BullMQ worker that does fetch(job.data.url)—which would cause the agent to ingest and act on untrusted, third-party web content supplied in job data.