nurec-index

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: This skill functions as a static router and informational index, containing no automated execution logic or sensitive data processing.
  • [EXTERNAL_DOWNLOADS]: The documentation references downloading official models and datasets from Hugging Face and cloning the primary NVIDIA repository. These are documented as legitimate vendor resources necessary for the described workflows.
  • [COMMAND_EXECUTION]: Provides instructions for repository cloning and Docker container management. It includes a specific security note in the discovery documentation that mandates obtaining user consent before the agent performs any network fetch or filesystem write.
  • [CREDENTIALS_UNSAFE]: Mentions environment variables like NGC_API_KEY and HF_TOKEN specifically to provide instructions on how to handle them safely, including warnings against insecure bash patterns that would echo secret values to the console.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 08:50 PM
Security Audit — agent-trust-hub — nurec-index