remotion-best-practices

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

• Third-party content exposure detected (high risk: 0.80). The skill includes explicit runtime fetches of arbitrary public URLs (e.g., rules/calculate-metadata.md uses fetch(props.dataUrl), and other rules use UrlSource/fetch for remote media or Lottie JSON), so the agent will ingest untrusted third‑party content that can materially change composition metadata and subsequent actions.