remotion-best-practices

Warn

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION] (MEDIUM): The transcription guidance in rules/transcribe-captions.md involves downloading and executing whisper.cpp binaries. Since the source is not in the trusted list, this requires review before execution.
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The rules/tailwind.md file instructs the agent to fetch instructions from an external URL at runtime, which is a potential vector for loading unverified instructions.
  • [COMMAND_EXECUTION] (SAFE): The skill suggests standard package manager commands to install Remotion-specific libraries. These are routine development tasks.
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection as it processes untrusted external data like .srt and .json caption files without explicit sanitization or boundary markers.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 07:11 AM