remotion-video-toolkit
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data (JSON props, remote media metadata, audio transcriptions) to generate video content. This represents a standard surface for indirect prompt injection common in data-driven video generation tools.
- Ingestion points: Data enters the agent context via
rules/calculate-metadata.md(external URL fetch),rules/compositions.md(API fetch), andrules/transcribe-captions.md(audio transcription). - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are included in the provided code templates.
- Capability inventory: The skill utilizes shell execution for rendering (
npx remotion render), network operations (fetch), and file system interactions for asset management. - Sanitization: The provided examples focus on functionality and do not include explicit input validation or sanitization, which is expected for instructional templates.
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install necessary dependencies using standard package managers. The targeted packages (
@remotion/*,mediabunny) are official or community-standard libraries for video processing. - [DYNAMIC_EXECUTION]: The skill makes use of Remotion's
calculateMetadataandbundlefeatures, which allow for runtime property calculation and code bundling, essential for dynamic video generation.
Audit Metadata