The StackBusiness & Tech• 1 min read

How security researchers used Anthropic to hack OpenAI

How security researchers used Anthropic to hack OpenAI

A newly discovered vulnerability + a bad SSO implementation + Claude Opus 5 = pwnage.

Read the full story at The Stack

Havoc links to the original reporting — the full story stays with the publisher.

Was this worth reading?Sign in to vote

More in Business & Tech

How Windows turned months of inactivity into a 7-hour update hostage situation

Windows is getting more efficient. The updates, not so much

Business & Tech The Stack

Runtime: Jev is an LLM without the LL

+ Rubrik has Mythos access and you don't, Splunk hugs servers, and an agent harness for Kubernetes.

Business & Tech The Register

Agentic security is the billion-dollar challenge for some clever startup to solve

High time to stop kicking the security can down the road, investor tells The Reg

Business & Tech