Check Point Research发现,ChatGPT的HTML预览沙箱保留的弹窗权限可被利用来绕过“锁定模式”,造成聊天数据被秘密外传、钓鱼或恶意软件投送。[1][2] “锁定模式”通过限制联网和外部服务能力,降低提示注入导致数据外泄的风险;但HTML预览是另一项应用功能,相关限制未能保护这条路径。[9][10] 这起事件提醒人们,AI产品的安全不仅取决于模型本身,也取决于应用如何隔离和处理不可信内容。[1][2]
What did Check Point Research discover about the ChatGPT Lockdown Mode bypass that OpenAI patched on September 18, 2026, how did Lockdown MoThe reported bypass used ChatGPT’s HTML preview sandbox, an application feature separate from the model’s safety controls.
AI 提示
Create a landscape editorial hero image for this Studio Global article: What did Check Point Research discover about the ChatGPT Lockdown Mode bypass that OpenAI patched on September 18, 2026, how did Lockdown Mo. Article summary: Check Point Research found an application-level weakness in ChatGPT’s HTML-preview sandbox that bypassed Lockdown Mode, enabling silent chat-data theft, phishing and malware delivery rather than defeating the model’s saf. Topic tags: general, general web. Style: premium digital editorial illustration, source-backed research mood, clean composition, high detail, modern web publication hero. Use reference image context only for broad subject, composition, and topical grounding; do not copy the exact image. Avoid: logos, brand marks, copyrighted characters, real person likenesses, fake screenshots, UI text, readable text, watermarks, charts with fake numbers, clic
openai.com
Check Point Research发现,ChatGPT代码块中的HTML预览功能存在漏洞,攻击者可借此绕过“锁定模式”。研究人员称,这条应用层攻击路径可能导致聊天数据被秘密外传,也可用于钓鱼和投送恶意软件。12
Check Point Research发现,ChatGPT的HTML预览沙箱保留的弹窗权限可被利用来绕过“锁定模式”,造成聊天数据被秘密外传、钓鱼或恶意软件投送。[1][2]
首先要验证的关键点是什么?
Check Point Research发现,ChatGPT的HTML预览沙箱保留的弹窗权限可被利用来绕过“锁定模式”,造成聊天数据被秘密外传、钓鱼或恶意软件投送。[1][2] “锁定模式”通过限制联网和外部服务能力,降低提示注入导致数据外泄的风险;但HTML预览是另一项应用功能,相关限制未能保护这条路径。[9][10]
Check Point Research发现,ChatGPT的HTML预览沙箱保留的弹窗权限可被利用来绕过“锁定模式”,造成聊天数据被秘密外传、钓鱼或恶意软件投送。[1][2] “锁定模式”通过限制联网和外部服务能力,降低提示注入导致数据外泄的风险;但HTML预览是另一项应用功能,相关限制未能保护这条路径。[9][10] 这起事件提醒人们,AI产品的安全不仅取决于模型本身,也取决于应用如何隔离和处理不可信内容。[1][2]
What did Check Point Research discover about the ChatGPT Lockdown Mode bypass that OpenAI patched on September 18, 2026, how did Lockdown MoThe reported bypass used ChatGPT’s HTML preview sandbox, an application feature separate from the model’s safety controls.
AI 提示
Create a landscape editorial hero image for this Studio Global article: What did Check Point Research discover about the ChatGPT Lockdown Mode bypass that OpenAI patched on September 18, 2026, how did Lockdown Mo. Article summary: Check Point Research found an application-level weakness in ChatGPT’s HTML-preview sandbox that bypassed Lockdown Mode, enabling silent chat-data theft, phishing and malware delivery rather than defeating the model’s saf. Topic tags: general, general web. Style: premium digital editorial illustration, source-backed research mood, clean composition, high detail, modern web publication hero. Use reference image context only for broad subject, composition, and topical grounding; do not copy the exact image. Avoid: logos, brand marks, copyrighted characters, real person likenesses, fake screenshots, UI text, readable text, watermarks, charts with fake numbers, clic
openai.com
Check Point Research发现,ChatGPT代码块中的HTML预览功能存在漏洞,攻击者可借此绕过“锁定模式”。研究人员称,这条应用层攻击路径可能导致聊天数据被秘密外传,也可用于钓鱼和投送恶意软件。12
Check Point Research发现,ChatGPT的HTML预览沙箱保留的弹窗权限可被利用来绕过“锁定模式”,造成聊天数据被秘密外传、钓鱼或恶意软件投送。[1][2]
首先要验证的关键点是什么?
Check Point Research发现,ChatGPT的HTML预览沙箱保留的弹窗权限可被利用来绕过“锁定模式”,造成聊天数据被秘密外传、钓鱼或恶意软件投送。[1][2] “锁定模式”通过限制联网和外部服务能力,降低提示注入导致数据外泄的风险;但HTML预览是另一项应用功能,相关限制未能保护这条路径。[9][10]