nemotron-super35
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown documentation and configuration files (INDEX.md, SKILL.md, and various files in paper/ and recipes/ directories). No scripts (.py, .js, .sh), binary executables, or dynamic code execution patterns are present.
- [SAFE]: All external URLs referenced in the documentation target well-known and trusted domains, including research.nvidia.com, github.com/NVIDIA-NeMo, and huggingface.co. These are used appropriately for citing technical reports and model artifacts.
- [SAFE]: The skill operates strictly as a retrieval-augmented knowledge base. It does not request or utilize tools for file system modification, network exfiltration, or credential access.
- [SAFE]: There are no detected patterns of prompt injection, obfuscation, or persistence. The instructions in SKILL.md are standard operational guidelines for an AI agent to locate, retrieve, and cite technical facts accurately.
Audit Metadata