skills/varghq/skills/video-sound/Gen Agent Trust Hub

video-sound

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes ffmpeg and ffprobe to perform audio analysis (loudness, silence detection, duration) and processing (mixing, fit, and muxing). Scripts such as sound.py, audition.py, and judge_takes.py execute these tools using the subprocess module with argument lists.
  • [EXTERNAL_DOWNLOADS]: The fetch.sh script and the audition.py tool perform network requests to download audio assets. These operations target vendor-owned infrastructure at s3.varg.ai and api.varg.ai to retrieve generated content such as voice lines and music beds.
  • [DYNAMIC_EXECUTION]: FFmpeg filter graphs are constructed at runtime in sound.py and judge_takes.py to handle tasks such as loudness normalization, audio crossfading, and visual waveform generation.
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a mechanism for ranking audio takes using an LLM judge. By interpolating user-supplied text and transcripts of audio recordings into prompts, it creates an attack surface where instructions embedded in the input data could potentially influence the judge's verdict.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 09:50 PM