Exo Cluster
PassAudited by ClawScan on May 16, 2026.
Overview
This is a user-directed setup guide for running an Exo local AI cluster; the main things to notice are external installs and LAN-exposed cluster/API services.
Install only from trusted Exo repositories, review commands before running them, and secure the LAN-facing master/API ports. This skill appears purpose-aligned and instruction-only, but running an AI cluster still means you are installing external software and exposing local services.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If an upstream repository or dependency changes, the code you install and run may differ from what the guide author expected.
The setup relies on external repositories and local package installation. This is expected for an Exo installation guide, but the artifacts do not pin commits or package versions.
git clone https://github.com/exo-explore/exo ... git clone https://github.com/tensorsofthewall/exo_windows ... pip install -e .
Use the official Exo sources where possible, inspect repositories before installing, and consider pinning known-good commits or releases.
Other devices on the reachable network may be able to interact with the cluster if the Exo service is exposed without protection.
The guide starts a master node, joins worker nodes over the network, and exposes a dashboard/API endpoint. This is central to a distributed cluster, but no authentication, TLS, or firewall boundaries are described.
python -m exo.main --role master --port 8080 ... python -m exo.main --role worker --master-addr 主节点IP:8080 ... http://主节点IP:52415
Run the cluster only on trusted networks, restrict ports with a firewall, and use any Exo-supported authentication or access controls before sending sensitive prompts or data.