cloudflare-workflows

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

• Third-party content exposure detected (high risk: 0.90). The skill includes code examples that fetch and deserialize data from arbitrary external URLs (e.g., fetch('https://api.example.com/files'), payment/processor endpoints, and uploadResult.downloadUrl) and ingests webhook payloads (req.json() for Stripe webhooks) — clearly showing the agent will read untrusted third‑party content as part of its workflow.