remotion-best-practices
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill documents techniques for ingesting data from external APIs and files, such as fetching JSON for composition metadata or captions. This introduces a surface where malicious external content could influence agent behavior, though the implementation follows standard development patterns.
- [INGESTION_POINTS]: fetch() calls in rules/calculate-metadata.md, rules/display-captions.md, and rules/import-srt-captions.md.
- [BOUNDARY_MARKERS]: None implemented in example code.
- [CAPABILITY_INVENTORY]: Includes shell command execution (ffmpeg), file system writes (fs module), and network requests (fetch).
- [SANITIZATION]: Examples prioritize functional implementation over input validation.
- [EXTERNAL_DOWNLOADS]: Documents the use of @remotion/install-whisper-cpp to download and install specialized binaries (Whisper.cpp) and AI models for speech-to-text processing.
- [COMMAND_EXECUTION]: Provides guidance on using CLI tools such as FFmpeg for video manipulation and the Remotion CLI for rendering and package management.
Audit Metadata