remotion-editor

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests arbitrary remote asset URLs (see rules/asset-lifecycle.md: fetch(remoteUrl) storing blobs) and then processes those assets (e.g., captioning/transcription in rules/captioning-workflow.md), so untrusted third-party content would be read and interpreted as part of the agent's workflow.