Remotion

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

• Third-party content exposure detected (high risk: 0.90). The ContentToAnimation workflow explicitly ingests content from open/public sources — e.g., arbitrary HTTP(S) article URLs, YouTube, and Twitter via the Parser (Workflows/ContentToAnimation.md: "Article URL", "YouTube URL", "Tweet/Thread" and "Route to appropriate Parser workflow") and other files show fetching remote assets (e.g., Tools/Ref-calculate-metadata.md uses fetch(props.dataUrl)), so the agent will read and interpret untrusted third‑party/user‑generated content at runtime.