remotion

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill implements patterns that ingest and process external data, creating an attack surface for indirect prompt injection.
  • Ingestion points: The skill fetches data from remote URLs in rules/calculate-metadata.md (props.dataUrl), rules/lottie.md (animation JSON), and rules/display-captions.md (caption JSON).
  • Boundary markers: No boundary markers or instructions to ignore embedded commands are present in the examples.
  • Capability inventory: The skill has access to command execution via FFmpeg (rules/ffmpeg.md) and file system writes during transcription (rules/transcribe-captions.md).
  • Sanitization: There is no evidence of sanitization or schema validation for the fetched external content before it is used in the rendering pipeline.- [COMMAND_EXECUTION]: The skill provides instructions for executing system commands for media processing and project configuration.
  • Media processing: Uses bunx remotion ffmpeg and ffprobe for video trimming and metadata extraction.
  • Dependency management: Includes numerous examples of using npx, npm, yarn, pnpm, and bun to add Remotion-specific packages.- [EXTERNAL_DOWNLOADS]: The skill facilitates the download of external resources required for its functionality.
  • Software binaries: Installs the Whisper.cpp binary and associated models for audio transcription using @remotion/install-whisper-cpp.
  • Assets: Fetches Lottie animations, Google Fonts, and remote video/audio assets from various domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 08:35 AM