mirror of
https://github.com/deepseek-ai/DeepSeek-R1.git
synced 2026-11-05 00:47:42 +00:00
[GH-ISSUE #839] [Security] 空对话中输入 '<think' 可泄露其他用户的对话碎片 #691
Labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/DeepSeek-R1#691
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @cancatchina on GitHub (May 11, 2026).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/839
(不加任何额外字符,不闭合标签)
4. 观察模型的回答。
预期结果
模型应报错、返回无关的通用回复、或对
<think标签进行安全转义。实际结果
模型返回了其他用户的不完整对话内容。例如在多次测试中,模型输出了类似“黑色区域积分”“请用文字描述图形边界”等与当前输入完全无关的文本,明显来自其他会话。
危害评估
附加说明
时间线
报告者:(可选填写您的昵称)
联系方式:(可选,建议使用临时邮箱)