cloudflare-queues

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts and enqueues arbitrary external HTTP payloads (see "HTTP Publishing (May 2025+)" and the producer webhook example app.post('/webhooks/:service') which sends untrusted third‑party/webhook content into queue.message.body for consumers to read and act on), so it clearly ingests untrusted public content that the agent will interpret.