skills/av/skills/pull-llamacpp-model/Gen Agent Trust Hub

pull-llamacpp-model

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the harbor command-line interface to update configuration parameters (harbor config set) and execute model retrieval tasks (harbor pull). These operations are consistent with the skill's stated purpose of managing a model inference environment.
  • [EXTERNAL_DOWNLOADS]: The skill references external Docker images, including a server image from the well-known ggml-org organization and a specialized image for AMD Strix Halo hardware (kyuz0/amd-strix-halo-toolboxes). These downloads are part of the standard deployment process for the tools described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 11:02 AM