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

doca-pcc

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation and workflows for using the doca-pcc library. It does not contain any executable scripts or binary payloads within the skill folder itself.
  • [SAFE]: All external references point to official NVIDIA documentation domains (docs.nvidia.com) or trusted GitHub repositories (github.com/NVIDIA-DOCA). These are verified vendor resources according to the provided context.
  • [SAFE]: The skill includes robust safety guidelines in CAPABILITIES.md and TASKS.md, emphasizing the 'triple-axis' verification method (BlueField generation, firmware slot enablement, and version matching) before performing any host-side operations.
  • [SAFE]: No hardcoded credentials, sensitive file access, or unauthorized network operations were identified. Instructions for using pkg-config and dpacc are standard for the DOCA development environment.
  • [SAFE]: The skill correctly identifies its own boundaries, refusing to invent algorithm bodies or provide pre-written code, which mitigates risks associated with unverified logic generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 05:55 AM
Security Audit — agent-trust-hub — doca-pcc