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 contains multiple workflow-level instructions that fetch and ingest open third-party content (e.g., calculate-metadata.md explicitly calls fetch(props.dataUrl) to transform composition props, lottie.md fetches Lottie JSON from assets4.lottiefiles.com, images/videos rules allow arbitrary remote URLs, and voiceover.md requires calling the ElevenLabs API), so the agent would read and act on untrusted public content that can materially influence behavior.