Parameter Labs 披露 ChatGPT 账户接管漏洞攻击链
原标题：How We Took Over ChatGPT Accounts
AI 摘要
Parameter Labs 披露了针对 ChatGPT HTML 预览（原 Canvas）沙箱机制的一条复杂攻击链：攻击者利用 MathLive 虚拟键盘的 postMessage 接收代码中的 innerHTML 注入，绕过沙箱新建无限制 iframe，再借 YouTube oEmbed 端点反射执行 JavaScript，最终可在用户访问分享链接时窃取私密数据或代其操作。OpenAI 已修复漏洞并支付 5000 美元赏金，作者认为该金额偏低。
正文节选
31st October 2026 - Link Blog How We Took Over ChatGPT Accounts (via) Parameter Labs describe an exploit they found against ChatGPT's implementation of the artifacts pattern (OpenAI used to call this "Canvas" but it looks like the latest revision is called HTML previews), where interactive custom HTML apps are displayed in a sandboxed iframe. It's important that HTML in these stays tightly sandboxed to avoid untrusted code interacting with OpenAI APIs and accessing private data. Parameter found