nemotron-retrieval-recipes
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements strict secret management guidelines, instructing agents to never ask users for API keys and to use environment variables or local configuration files instead.
- [SAFE]: It enforces a 'dry-run first' policy, requiring agents to validate configurations with help commands and dry-run flags before initiating long-running, remote, or resource-intensive tasks.
- [SAFE]: All remote resources, including datasets on Hugging Face and container images on the NVIDIA NGC registry, originate from well-known and trusted organizations.
- [SAFE]: The skill includes explicit data governance warnings, advising users to check privacy policies before submitting proprietary data to synthetic data generation (SDG) endpoints.
- [SAFE]: Instructions for remote execution via Slurm or other clusters include mandatory prerequisite checks and local validation steps to prevent accidental or unauthorized resource consumption.
Audit Metadata