remotion-best-practices

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill frequently instructs the agent to execute package installation commands (e.g., npx remotion add, npm i, yarn add) to set up various Remotion plugins and dependencies. While these are standard for the development environment, they involve the execution of external CLI tools and scripts.
  • [INDIRECT_PROMPT_INJECTION]: Multiple rules (such as rules/calculate-metadata.md, rules/import-srt-captions.md, and rules/lottie.md) describe patterns where the agent fetches data from external URLs (JSON, SRT, or Lottie files) to populate component props and metadata.
  • Ingestion points: Network fetch() calls are used to retrieve external content in rules/calculate-metadata.md, rules/import-srt-captions.md, and rules/lottie.md.
  • Boundary markers: The provided code examples do not include boundary markers or explicit instructions to ignore potentially malicious embedded instructions in the fetched data.
  • Capability inventory: The fetched data is used to define composition properties, render text/captions, and configure animations, which are then processed by the Remotion engine.
  • Sanitization: There is no evidence of sanitization, validation, or schema enforcement (beyond standard JSON parsing) for the retrieved external content in the provided examples.
  • [EXTERNAL_DOWNLOADS]: The skill makes extensive use of the mediabunny package for media inspection Tasks (duration, dimensions, track analysis). This is a third-party dependency used throughout the media-related rules.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 01:53 PM