image-to-video-shots

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes subprocess to call ffmpeg, ffprobe, and fc-list. These operations are fundamental to the skill's primary function of video and audio processing. The implementation uses list-based arguments rather than shell strings, which mitigates common shell injection vulnerabilities.
  • [EXTERNAL_DOWNLOADS]: The tts_edge.py script connects to Microsoft's Edge TTS service to generate voiceovers. This involves network communication with a well-known, established cloud service.
  • [INDIRECT_PROMPT_INJECTION]: The tool ingests user-provided data from storyboard.json to generate subtitles and prompts. While this represents an attack surface for indirect injection, the scripts include sanitization (such as escaping curly braces in subtitle markup) to prevent the manipulation of downstream media filter syntax.
  • [SAFE]: The skill relies on standard Python libraries (e.g., pillow, numpy) and industry-standard media utilities. All external repository references point to the author's official GitHub organization or trusted services.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 03:16 PM