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

doca-comch

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's instructions are consistent with its stated purpose of aiding DOCA Comch development. No malicious patterns, prompt injections, or obfuscation were detected.
  • [COMMAND_EXECUTION]: The skill suggests running standard system commands for environment verification and debugging, such as ls, lspci, pkg-config, mlxconfig, and dmesg. Use of sudo is appropriately limited to commands requiring elevated privileges for hardware diagnostics on the BlueField DPU, which is a standard requirement for this domain.
  • [EXTERNAL_DOWNLOADS]: The skill references official NVIDIA documentation and public GitHub repositories for SDK documentation and samples. These are trusted sources and do not involve execution of untrusted remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 05:55 AM
Security Audit — agent-trust-hub — doca-comch