pull-llamacpp-model
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
harborcommand-line interface to modify system configurations viaharbor config set. These commands are used to change and subsequently restore the container image used for model inference, which is the stated purpose of the skill. - [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch a Docker image from
ghcr.io/ggml-org/llama.cpp:server. This repository belongs to the official organization responsible for the llama.cpp project, a well-known service in the AI community. - [EXTERNAL_DOWNLOADS]: The skill references and restores a custom Docker image
kyuz0/amd-strix-halo-toolboxes:rocm-7.2. The instructions explicitly state this image is required for specific AMD hardware support (Strix Halo / gfx1151) that is not available in official ROCm builds.
Audit Metadata