remotion-best-practices

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill content is restricted to legitimate Remotion best practices and coding standards.
  • [COMMAND_EXECUTION]: Contains instructions for standard package management and media processing using npx, bunx, and ffmpeg within the Remotion ecosystem.
  • [EXTERNAL_DOWNLOADS]: References the installation of various Remotion-specific npm packages and the download of Whisper.cpp binaries and models for audio transcription.
  • [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface through dynamic data ingestion.
  • Ingestion points: External data is fetched from URLs and project props in calculateMetadata.md, compositions.md, and lottie.md.
  • Boundary markers: None identified in the provided templates.
  • Capability inventory: Includes shell command execution for tool installation in rules/3d.md, rules/ffmpeg.md, rules/fonts.md, and rules/parameters.md, as well as file system writes for saving generated captions in rules/transcribe-captions.md.
  • Sanitization: Content fetched from external sources is processed without explicit sanitization steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 03:16 AM
Security Audit — agent-trust-hub — remotion-best-practices