vox-director

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a legitimate workflow for video production, coordinating between local scripts and a cloud-based API. All referenced operations are consistent with the stated purpose of generating narrated collage animations.
  • [COMMAND_EXECUTION]: The skill requires the agent to execute local Python scripts (e.g., keyframes.py, clips.py, audio.py) and ffmpeg commands for media assembly. These actions are restricted to the skill's project directory and are standard for media-oriented agent tasks.
  • [EXTERNAL_DOWNLOADS]: Communicates with the Atlas Cloud API (api.atlascloud.ai) to fetch model configurations and download generated media assets via curl. These network operations target a well-known service associated with the skill's functionality.
  • [CREDENTIALS_UNSAFE]: Securely manages authentication by instructing the agent to verify the ATLASCLOUD_API_KEY environment variable. It avoids hardcoding secrets and follows industry-standard practices for API key management.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 09:32 AM
Security Audit — agent-trust-hub — vox-director