remotion-markup

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for fetching and processing external data that influences the rendering and logic of video compositions.
  • Ingestion points: calculate-metadata.md describes fetching JSON data from a URL provided in props; lottie.md demonstrates fetching animation data from remote URLs.
  • Boundary markers: The guidance does not include specific markers or instructions to the agent to ignore any natural language instructions that might be embedded within the external data.
  • Capability inventory: The skill utilizes network fetch operations and the example voiceover script includes file system write capabilities (writeFileSync).
  • Sanitization: The provided code examples do not incorporate sanitization or strict schema validation for the fetched external content before it is used to define composition properties.
  • [EXTERNAL_DOWNLOADS]: The skill references several external sources for media assets and sound effects.
  • Fetches media and sound effects from official Remotion infrastructure (remotion.media).
  • References animation assets from the LottieFiles platform (lottiefiles.com).
  • Provides a reference to a third-party repository on GitHub (kapishdima/soundcn) for additional sound effects.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 02:05 PM