How-to

AI 编程智能体部署安全漏洞的频率是人工写码的 3.4 倍

Why we picked it

如果你在用 Cursor 或 Copilot 这类智能体写代码,这条值得看:Checkmarx 数据说智能体代码的安全问题是手写的 3.4 倍,它的 IDE 扩展能让智能体自己发现并修掉漏洞,有免费试用。

Checkmarx 的报告显示,使用 AI 编程智能体写代码的开发者,部署安全问题代码的比例是手工写码的 3.4 倍。Checkmarx 推出了 Developer Assist IDE 扩展,可以在 IDE 内扫描并识别代码中的安全问题。

Body

该扩展的工作方式是与编程智能体协作:扫描发现漏洞后,直接让智能体自动修复,形成检测加修复的闭环,而不是开发者手动改。文中附带了免费试用链接。

这条信息对正在用 Copilot、Cursor 等智能体工具的团队有参考意义:AI 提速的同时引入了更多安全债务,需要把安全扫描嵌入工作流来对冲,而不是事后人工审计。

Original · Ate-a-Pi

People writing code with agents are deploying security issues at 3.4x the rate of those who write code manually.

This is how you can identify and fix security issues in your code:

• Install the @Checkmarx Developer Assist extension in your IDE • It will identify any security issues • It will work with your agent to automatically fix them

Here is the free trial: https://t.co/C6dEfjzxwz

Thanks to the team for sharing their report and collaborating with me on this post.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Checkmarx, coding assistants, AI safety, agents.

Source attribution: curated from Ate-a-Pi (@svpino).