nemo-automodel-recipe-development

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill serves as a technical guide for the NeMo AutoModel framework. Technical analysis of the instructions, examples, and YAML structures revealed no evidence of prompt injection, data exfiltration, or malicious intent.
  • [EXTERNAL_DOWNLOADS]: The skill references well-known and trusted external resources, including model identifiers from Hugging Face (e.g., meta-llama/Llama-3.2-1B) and official NVIDIA documentation domains. These references are standard for machine learning development workflows.
  • [COMMAND_EXECUTION]: Benign shell command examples such as automodel finetune llm -c config.yaml are included to demonstrate how to validate and run training recipes. These commands are scoped to the primary purpose of the skill and do not perform unauthorized or destructive system operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 10:58 AM
Security Audit — agent-trust-hub — nemo-automodel-recipe-development