remotion

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use standard shell commands for project initialization and video rendering. Evidence includes usage of npx create-video@latest, npm i, and npx remotion (subcommands: studio, render, still, lambda).
  • [EXTERNAL_DOWNLOADS]: The documentation references multiple official packages from the @remotion ecosystem for extended functionality. Referenced packages include remotion, @remotion/transitions, @remotion/google-fonts, @remotion/three, @remotion/gif, @remotion/lottie, @remotion/media-utils, @remotion/captions, @remotion/zod-types, and @remotion/media.
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates an API pattern (calculateMetadata) that fetches external JSON data to determine video properties like duration. Ingestion points: SKILL.md (in the calculateMetadata async function example). Boundary markers: Absent in the documentation example. Capability inventory: The skill allows network fetching (fetch) and subsequent video frame generation. Sanitization: The provided example does not include data validation or sanitization of the external JSON payload before usage.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 02:56 PM
Security Audit — agent-trust-hub — remotion