remotion

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

• Third-party content exposure detected (high risk: 0.80). The skill's rules explicitly instruct the agent to fetch and ingest arbitrary remote URLs (e.g., calculate-metadata.md uses fetch(props.dataUrl) to set composition props, rules/assets.md and rules/videos.md allow remote Img/Video/Audio URLs, rules/lottie.md fetches remote Lottie JSON, and multiple mediabunny helpers use UrlSource(src)), meaning untrusted third-party content is read and its data can directly change props, durations, metadata and rendering behavior.