skills/nvidia/skills/doca-rdmi/Gen Agent Trust Hub

doca-rdmi

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to provide documentation and structured workflows for the DOCA RDMI library, which is a legitimate part of the NVIDIA DOCA SDK.
  • [SAFE]: All referenced command-line tools (such as "pkg-config", "doca_caps", "mlxconfig", and "dmesg") are standard utilities for managing and debugging NVIDIA hardware and software environments.
  • [SAFE]: The skill explicitly forbids the agent from authoring source code for experimental APIs from scratch, requiring a user-provided baseline. This mitigation reduces the risk of generating incorrect or potentially unsafe code.
  • [SAFE]: No evidence of data exfiltration, credential theft, or malicious obfuscation was found. The use of "sudo" in documentation is appropriately scoped to necessary hardware diagnostic tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 05:55 AM
Security Audit — agent-trust-hub — doca-rdmi