ltx2
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documents the use of a local Python script (
tools/ltx2.py) to interface with a remote inference endpoint. These commands are standard for the skill's primary purpose of video generation. - [CREDENTIALS_SAFE]: The setup instructions correctly advise storing sensitive API tokens and endpoint URLs in a
.envfile or using platform-specific secret management (e.g.,modal secret create), which is a security best practice. - [EXTERNAL_DOWNLOADS]: The skill mentions downloading model weights from Hugging Face during the deployment process (
modal deploy). Hugging Face is a well-known service in the AI community, and these operations are expected for a large-scale model deployment.
Audit Metadata