一句话：构建 ChromeSecBench，实证揭示 LLM 生成框架约束程序存在高漏洞率，且推理模型更不安全。
本文研究 LLM 生成受框架约束程序时的安全性问题。作者聚焦 Chrome 扩展，因其涉及多重权限边界和隔离组件。为此构建 ChromeSecBench，含 140 个基于已知漏洞扩展的提示，指示 9 个先进 LLM 生成完整扩展，并从场景类型、模型差异和漏洞类别三维度分析。结果显示，LLM 生成漏洞程序的比例高达 18%-50%，在认证与身份和 Cookie 管理场景中分别可达 83% 和 78%；多数漏洞将 cookie、历史记录或书签等敏感浏览器数据暴露给不可信代码。此外，高级推理模型表现更差，比简单模型产生更多漏洞，揭示 LLM 编码能力与安全编写框架约束程序能力之间的关键差距。
In recent years, the AI wave has grown rapidly in software development. Even novice developers can now design and generate complex framework-constrained software systems based on their high-level requirements with the help of Large Language Models (LLMs). However, when LLMs gradually "take the wheel" of software development, developers may only check whether the program works. They often miss security problems hidden in how the generated programs are implemented. In this work, we investigate the security properties of framework-constrained programs generated by state-of-the-art LLMs. We focus specifically on Chrome extensions due to their complex security model involving multiple privilege boundaries and isolated components. To achieve this, we built ChromeSecBench, a dataset with 140 prompts based on known vulnerable extensions. We used these prompts to instruct nine state-of-the-art LLMs to generate complete Chrome extensions, and then analyzed them for vulnerabilities across three dimensions: scenario types, model differences, and vulnerability categories. Our results show that LLMs produced vulnerable programs at alarmingly high rates (18%-50%), particularly in Authentication & Identity and Cookie Management scenarios (up to 83% and 78% respectively). Most vulnerabilities exposed sensitive browser data like cookies, history, or bookmarks to untrusted code. Interestingly, we found that advanced reasoning models performed worse, generating more vulnerabilities than simpler models. These findings highlight a critical gap between LLMs’ coding skills and their ability to write secure framework-constrained programs.
@inproceedings{abs-2510-16823,
title = {When AI Takes the Wheel: Security Analysis of Framework-Constrained Program Generation},
author = {Yue Liu and Zhenchang Xing and Shidong Pan and Chakkrit Tantithamthavorn},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3773142}
}