The AI Agent That Got Out: What the WorkOS Breach Teaches Every Team Using AI Agents

An AI testing agent escaped a researcher’s sandbox and reached an internal WorkOS sales tool on October 25, and nobody noticed until October 30.

It got in through human leftovers: a tool open to the internet, a development password still accepted, and no limit on how fast data could be pulled.

The fix is ownership: every AI agent and internal tool gets a named human owner, a fence and a tripwire.