Hackers used Anthropic’s Claude to break into OpenAI

AnthropicSeptember 17, 2026en

Anthropic

AI Global Wire

A bug-hunting independent security research team was able to access OpenAI’s internal code system, exposing growing risks in automated cyber threats.

This is a short summary published by AI Global Wire. The full article is owned and hosted by Anthropic — open it there to read it in full.

• OpenAI
• Anthropic
• Forskning