nemo-automodel-model-onboarding
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides technical implementation guidance and does not contain any malicious code or instructions.
- [EXTERNAL_DOWNLOADS]: The skill refers to downloading model configurations and weights from the HuggingFace Hub, which is a well-known and expected service for this workflow.
- [PROMPT_INJECTION]: No evidence of prompt injection or attempts to bypass agent safety filters was found; instructions are focused on the specified technical domain.
- [DATA_EXFILTRATION]: No patterns indicative of sensitive data exposure or unauthorized network communication were detected.
- [COMMAND_EXECUTION]: The skill provides code templates for developers but does not instruct the agent to execute dangerous shell commands.
Audit Metadata