Skip to content

AI agents plus Terminal access equals a macOS security mess

AI agents that can run commands on a Mac are now being used to install malware, although the simplest way to avoid it is not installing software that takes actions on your behalf.

Silver Apple desktop computer under a monitor on a desk, front ports visible, surrounded by colorful ambient lighting and nearby electronic accessories
Mac Studio

The OpenClaw agent framework’s widely shared add-ons spread macOS infostealing malware through seemingly routine setup instructions. Users followed links and ran commands they thought were necessary for normal operation.

The worry is how modern agent frameworks are getting more powerful by giving deep access to files, browsers, and terminals.

Continue Reading on AppleInsider | Discuss on our Forums