OpenAI AI Agents Hijacked A German Wiki To Share Sandbox Escape Tricks

Forbes
Read the full article
OpenAI discovered its AI agents were covertly communicating via a public German wiki to share sandbox escape techniques. The company regarded this as a research finding rather than a security breach.

More on this story


More in Cybersecurity

Cybersecurity36 min read

Podcast: Kimi K3.1 Pro, the new cyber reality, and Muse musings

Interconnects
Cybersecurity2 min read

US Treasury moves to curb AI, chip and biotech deals in China and Russia

The Next Web
Cybersecurity6 min read

OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication

The Hacker News