OpenAI Hacked by Small Team of White Hat Security Researchers Using Anthropic's Claude Opus 5

Security Researchers Hacked Into OpenAI Using Anthropic’s Claude

OpenAI paid the researchers a $6,500 bug bounty, but the incident once again highlights the growing cybersecurity threats posed by advanced AI agents.

OpenAI hacked by small team of white hat security researchers using Anthropic's Claude Opus 5

For enterprise teams, the larger lesson extends beyond one vulnerable image decoder. AI agents are increasingly being given credentials and connectors that span source code, communications and corporate data.

Hackers Were Able To Use Claude To Hack OpenAI Employee Accounts And Create A PR In Its Repo

AI is helping people exploit cybersecurity vulnerabilities — and even the AI labs theselves aren’t safe. A team of security researchers has revealed...

OpenAI hacked by small team of white hat security researchers using Anthropic's Claude Opus 5 | #hacking | #cybersecurity | #infosec | #comptia | #pentest | #hacker - National Cyber Security Consulting

Security researchers say they used Anthropic’s newly released Claude Opus 5 to help turn an image-processing vulnerability into an exploit chain that compromised an OpenAI employee’s ChatGPT account and reached the company’s internal GitHub environment — an incident that illustrates how AI coding agents are changing the economics of sophisticated vulnerability exploitation. The researchers, part […] Thank you for subscribing to our RSS feed!

华尔街日报：黑客利用 Anthropic Claude 入侵 OpenAI 内部系统

ChainCatcher 消息，据《华尔街日报》报道，独立安全研究团队利用 Anthropic 的 Claude 软件攻破 OpenAI 一名员工的 ChatGPT 账户，得以访问并修改该员工关联的 OpenAI 内部代码系统。研究人员先利用 Claude 分析 OpenAI 开发者社区所使用的 Discourse 漏洞并生成可运行的攻击代码，随后获取认证令牌，并借助权限配置问题进入一名 OpenAI 员工的 ChatGPT 账户，同时取得对部分私有 GitHub 代码库的有限读取和提交修改建议权限。