heygen-digital-avatar

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/compose_circle_avatar.py utilizes subprocess.run to call ffmpeg, ffprobe, and the macOS swift interpreter. These tools are used for video metadata extraction, frame sampling, and final video composition. The swift command executes a local script scripts/measure_face_center.swift to perform face detection using the Vision framework. These operations are consistent with the skill's primary function of video production and do not indicate malicious intent.
  • [PROMPT_INJECTION]: The instructions establish a robust multi-step verification process, requiring the agent to wait for explicit user confirmation of audio auditions before proceeding to paid video generation. This human-in-the-loop control is a positive safety feature that prevents unauthorized or accidental credit consumption on the HeyGen platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 08:46 AM
Security Audit — agent-trust-hub — heygen-digital-avatar