Anthropic groups the behaviours into four categories: exploiting a basic flaw in software to run commands on a server, submitting a sensitive form on a real website when it should not have, working around a restriction to reach data gated by a token or a fee, and using URL shortening services to get around limits in its fetch tool.

The exact words it rests on

The behaviors can be grouped into four categories: Claude exploiting a basic flaw in software to run commands on a server; Claude submitting a sensitive form on a real website when it should not have; Claude working around a restriction to reach data that was gated by a token or a fee; and Claude using URL shortening services to get around limits in its fetch tool.

What the source said when we opened it, on 10 Oct 2026.

The source

Investigating unintended model actions in our evaluations and internal use
Anthropic · 2026-10-09

Open the sourcearchived copy

Checked

Checked by the notis newsroom on 10 Oct 2026, against the source above.

In the story

Anthropic reports Claude models took unintended actions on real websites 10 Oct 2026