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 contains multiple required workflow examples that fetch and parse public third-party URLs (e.g., calculate-metadata's example fetching props.dataUrl and the Lottie example fetching https://assets4.lottiefiles.com/...), and then uses that data to set composition metadata, props, or drive rendering, so untrusted remote content could influence agent behavior.