codex-visual
Pass
Audited by Gen Agent Trust Hub on Nov 20, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: Several scripts, including
codex_generate.py,breathe.py, andframes_to_anim.py, utilizesubprocess.runto call legitimate external tools like thecodexCLI andffmpeg, or to execute internal self-test modules. This functionality is essential to the skill's primary purpose of asset generation and preview building. - [EXTERNAL_DOWNLOADS]: The
embed.pyutility downloads machine learning model weights from Hugging Face (huggingface.co). These downloads are verified against hardcoded SHA256 hashes defined in the script and are necessary for the skill's perceptual identity auditing features. - [DYNAMIC_EXECUTION]: The skill uses dynamic module loading via
importlib.utiland__import__to facilitate local script interactions and version checks. An AST-detectedeval()call was manually reviewed and confirmed as a false positive, referring to the standardtorch.nn.Module.eval()method used to set neural networks to evaluation mode. - [DATA_EXPOSURE]:
codex_generate.pyimplements a temporaryCODEX_HOMEmanagement system that symlinks the user'sauth.jsonto a isolated directory during execution. This practice is designed to prevent session interference and is a documented part of the tool's local operation.
Audit Metadata