Ubuntu Ollama

Ubuntu Ollama — run Ollama on Ubuntu with fleet routing across multiple Ubuntu machines. Ubuntu Ollama setup with apt, systemd, and NVIDIA CUDA. Route Ollama...

This skill appears to do what it says (set up an Ollama fleet), but it requires running network installers and creating system-level services — treat it like any other system service install: 1) Verify upstream sources: confirm the ollama.ai installer and the 'ollama-herd' package are the official/reputable releases referenced by the GitHub repo listed in the skill. 2) Inspect the code/package before pip installing (or install in an isolated environment/container/VM). 3) Avoid piping unknown scripts directly into sh; download and review the installer first. 4) Be cautious about enabling an unauthenticated HTTP endpoint on port 11435 — restrict access with firewall rules, network segmentation, or enable authentication if supported. 5) If you must try it on production hosts, prefer testing in a sandboxed environment and verify service behavior (auth, logging, resource usage) before rolling out to multiple machines.

Type: OpenClaw Skill Name: ubuntu-ollama Version: 1.0.0 The skill provides instructions for setting up a distributed Ollama environment using 'ollama-herd', which involves high-risk actions such as executing a remote installation script (curl | sh for Ollama) and creating systemd services with sudo privileges. While the behavior appears aligned with the stated purpose and includes defensive guardrails for the AI agent in SKILL.md, the requirement for system-level modifications and remote code execution during setup meets the threshold for a suspicious classification due to the inherent risks of these capabilities.