sqsl-video-to-article

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONNO_CODE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands via subprocess.run to interact with ffmpeg and whisper-cli. These calls use structured argument lists (not raw strings), which prevents command injection. The operations are limited to media processing (audio extraction, transcription, and frame extraction) on local video files as requested by the user.
  • [SAFE]: The skill uses a local glossary.json file for post-processing transcription errors. This is a standard and safe method for improving ASR (Automatic Speech Recognition) accuracy for specific brand names and terminology.
  • [SAFE]: No network requests or data exfiltration patterns were detected. All processing (transcription and image extraction) is performed locally on the user's machine using local models and binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 08:11 AM
Security Audit — agent-trust-hub — sqsl-video-to-article