skills/nvidia/skills/nvmolkit-usage/Gen Agent Trust Hub

nvmolkit-usage

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing nvmolkit and torch from official GitHub repositories and pytorch.org. These references are established vendor resources and well-known services.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests SMILES molecular data using the RDKit library parser. Analysis of the provided scripts confirms no high-risk capabilities such as network operations, file writing, or shell execution are integrated with this data input.
  • [SAFE]: No malicious patterns, obfuscation, or safety bypasses were identified in the skill documentation, metadata, or scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 12:34 PM