# GLM-5.3 发现 Cursor 严重漏洞，安全测试分数大涨

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-08-15 08:06
- AIHOT 分数：42
- AIHOT 链接：https://aihot.virxact.com/items/cmstmttw80cecro0x8btcwkxm
- 原文链接：https://x.com/rohanpaul_ai/status/2088416903572410456

## AI 摘要

GLM-5.3 在复杂逆向工程任务中发现 Cursor 存在潜在严重漏洞，已私下披露并正与 Cursor 团队合作修复。其 CyberGym 安全测试得分升至 84.5%，ExploitBench 得分从 24.4% 翻倍至 54.4%。智谱称 GLM-5.3 仅通过扩展后训练实现性能提升，未进行额外预训练。

## 正文

So GLM-5.3 has already found a "potentially serious vulnerability" in Cursor.

GLM-5.3's CyberGym score rose to 84.5%, while ExploitBench more than doubled from 24.4% to 54.4%.

Shows how much more performance a frontier-scale base model can deliver without going through another costly pretraining run.

"Scaling post-training is all we did for GLM-5.3," Z .ai said in its technical announcement.

### 引用推文

> Lou：We gave GLM-5.3 a complex reverse-engineering task. It found a potentially serious vulnerability in Cursor. We disclosed it privately. Appreciate Cursor team is...