remotion-expert

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches and ingests external, potentially untrusted content (e.g., calculateMetadata uses fetch(https://api.v2.com/data/${props.id}) / fetch(https://api.v2.com/video-data/${props.id}), references prefetch('https://example.com/video.mp4'), and uses external Audio src URLs) and then uses that data as props/content for rendering, so the agent would read/interpret third‑party content and could be exposed to indirect prompt injection.