cloudflare-vectorize

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

• Third-party content exposure detected (high risk: 0.90). The document-ingestion template explicitly fetches arbitrary web pages (fetch(body.url) in templates/document-ingestion.ts, route POST /ingest/url), extracts their text and ingests it into the index, so untrusted public web content can be read and used by the agent enabling indirect prompt injection.