Anthropic has begun previewing "auto mode" inside of Claude Code. The company describes the new feature as a middle path between the app's default behavior, which sees Claude request approval for every file write and bash command,

Anthropic has released new tools on Claude, called Code and Cowork, which now let the chatbot control Mac computers and let users do work or accomplish tasks remotely.

Anthropic also warns that, when computer use is activated, Claude will be able to see anything visible on-screen, including “personal data, sensitive documents, or private information.” For all these reasons, the company recommends “starting with the apps you trust and not working with sensitive data” during this research preview stage.

Kaspersky has discovered infostealers mimicking Claude Code, OpenClaw and other AI developer tools as demand for Anthropic's chatbot grows.