remotion-best-practices

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

• Third-party content exposure detected (high risk: 0.90). The skill clearly fetches and ingests arbitrary remote assets that it then parses or renders (e.g., rules/lottie.md fetch('https://assets4.lottiefiles.com/...') to load Lottie JSON, rules/calculate-metadata.md fetch(props.dataUrl) for composition props, and multiple rules allowing remote // or fetching SRTs), meaning the agent will read and interpret untrusted third‑party content.