Researchers Used Anthropic's Claude to Hack Into OpenAI's Own Systems
6 Articles
6 Articles
Madrid, 18 Sep (EFE).- A team of security researchers has used Claude, the artificial intelligence (IA) of Anthropic, to access the ChatGPT account of an OpenAI employee and, through it, to consult files and propose changes to a private repository of software of the company. [...] The post A team of researchers checked OpenAI with Claude, the AI of Anthropic, according to a medium was first published in HolaNews.
Independent IT security researchers have managed to gain access to the ChatGPT account of an OpenAI employee and, through it, to an internal company code, using artificial intelligence tools developed by the Anthropic rival.
Cybersecurity specialists from Hacktron AI gained access to the OpenAI employee's account with Claude and, through it, to the company's internal code. Under the Bug Bounty program, researchers received $6,500 for their work.
Researchers Used Anthropic's Claude to Hack Into OpenAI's Own Systems
Security researchers at Hacktron AI used Anthropic's Claude Opus 5 to weaponize a libheif image-processing bug into a full exploit chain, breaching an OpenAI employee's ChatGPT account and reaching OpenAI's internal GitHub environment in under 72 hours. The Wall Street Journal independently confirmed the breach, and both Discourse and OpenAI have since patched the underlying flaws.
Cybersecurity researchers discovered and exploited a security flaw that gave them access to an OpenAI employee's ChatGPT account
Questions are once again being raised about the security of OpenAI, now that ethical hackers were able to gain access to an OpenAI employee's account. They did so using a model from rival Anthropic.
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
