tao-train-bevfusion
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill correctly identifies its reliance on the official NVIDIA container registry for task execution, which is a trusted source for this vendor-authored skill.
- [NO_CODE]: The skill does not include any executable scripts (e.g., Python, Bash, or JavaScript files) in its distribution. It consists solely of documentation, metadata, JSON schemas, and YAML configuration templates.
- [SAFE]: Instructions provide legitimate technical guidance for multi-sensor 3D perception workflows and do not attempt to bypass safety filters, override agent guidelines, or access sensitive system resources.
- [SAFE]: No evidence of data exfiltration or credential leakage was found. Logging and monitoring configurations (such as Weights & Biases) follow standard machine learning development practices.
Audit Metadata