Researchers say they compromised multiple OpenAI employees' ChatGPT accounts

ChengleiSi · x · 2026-09-18

A security research team (@rootxharsh, @S1r1u5, @iamnoooob) says that in July it compromised multiple OpenAI employees' ChatGPT accounts, claiming that in theory any ChatGPT connector—including Slack, GitHub, and email integrations—could be affected. Details are being published in a thread; the full attack methodology and OpenAI's response remain to be seen.

Related event: Researchers Used Claude to Breach OpenAI's Internal Codebase(22 posts)→

Original post →

More from Safety

Safety channel →