cloudflare-vectorize

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

• Third-party content exposure detected (high risk: 0.90). The skill's document-ingestion template (templates/document-ingestion.ts) and SKILL.md include a /ingest/url flow that fetches arbitrary public URLs via fetch(body.url), extracts page text, and ingests it into the Vectorize index—meaning untrusted third‑party web content is read and can directly influence search/RAG results and subsequent agent actions.