create-jump-cuts

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/jump_cut.py utilizes subprocess.run and subprocess.check_output to execute ffmpeg and ffprobe commands for video analysis and editing. The analysis confirms that these calls use list-based arguments (not shell strings), which prevents command injection vulnerabilities even when handling user-provided file paths.- [SAFE]: The skill contains no network activity, external downloads, or use of remote code execution patterns. All operations are performed locally on the input video and transcript files provided by the user. The skill adheres to its documented purpose without any deceptive or hidden behaviors.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 04:39 PM
Security Audit — agent-trust-hub — create-jump-cuts