remotion-video-creation

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides examples of ingesting untrusted external data to dynamically set composition duration, dimensions, and properties.
  • Ingestion points: rules/calculate-metadata.md fetches data from a user-supplied props.dataUrl. rules/compositions.md fetches data based on a props.videoId. rules/tailwind.md instructs the agent to fetch documentation from an external URL.
  • Boundary markers: The provided code snippets do not implement delimiters or specific instructions for the AI to ignore instructions embedded within the fetched content.
  • Capability inventory: The skill uses fetch for network operations and sets video metadata based on the response.
  • Sanitization: No input validation or content sanitization is demonstrated in the examples.
  • [COMMAND_EXECUTION]: The skill includes instructions for installing official framework extensions using package managers (npx remotion add, bunx, yarn, pnpm). These commands target official scoped packages such as @remotion/three and @remotion/media.
  • [EXTERNAL_DOWNLOADS]: The skill references several remote assets from well-known domains, including Remotion's official media host and LottieFiles, for use in video compositions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:01 AM
Security Audit — agent-trust-hub — remotion-video-creation