skills/nvidia/nurec-skills/ncore/Gen Agent Trust Hub

ncore

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, prompt injections, or persistence mechanisms were detected in the skill.
  • [DATA_EXPOSURE]: The documentation includes a security-positive instruction on how to safely verify the presence of an HF_TOKEN environment variable. It recommends using a length-based check to avoid echoing the actual token value to terminal history or logs.
  • [EXTERNAL_DOWNLOADS]: The skill references downloads from official NVIDIA GitHub repositories (github.com/NVIDIA/ncore) and public package registries (PyPI). These are appropriate for the skill's stated purpose and originate from the trusted vendor.
  • [COMMAND_EXECUTION]: Instructions describe the use of standard development and build tools such as Bazel, Git, and Pip for installing and running conversion utilities. These operations are scoped to the intended workflow of preparing sensor datasets.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 08:49 PM
Security Audit — agent-trust-hub — ncore