nemo-automodel-distributed-training

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely documentation-based, providing patterns for configuring tensor, pipeline, context, and expert parallelism in the NeMo framework. It does not include executable scripts or perform any system operations.
  • [SAFE]: No evidence of prompt injection or behavioral overrides was detected. The instructions are focused on scoping the agent's response to the provided technical documentation.
  • [SAFE]: All external references point to official NVIDIA domains and GitHub repositories (docs.nvidia.com and github.com/NVIDIA-NeMo), which are well-known and trusted sources.
  • [SAFE]: No sensitive data access, credential exposure, or exfiltration patterns were identified. The file paths mentioned are internal repository structures used as documentation anchors.
  • [SAFE]: The skill does not perform remote downloads, package installations, or dynamic code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 04:34 PM
Security Audit — agent-trust-hub — nemo-automodel-distributed-training