Google 披露 PageBreak AI 安全智能体，已发现 500 多个 XSS 漏洞
原标题：Google Discloses PageBreak AI Security Agent That Found 500+ XSS Bugs
AI 摘要
Google 披露其 AI 安全智能体 PageBreak 自 1 月全面运行以来，已在自家 Web 应用中自主发现 500 多个 XSS 漏洞。该系统基于 Gemini 模型提出漏洞假设，但只有在确定性验证器于运行环境中成功复现利用后才上报，因此误报率接近零。Google 还计划将其与 CodeMender 等智能体安全项目集成，自动生成修复方案，不过 500 多个漏洞尚未经过独立验证。
正文节选
According to a paper published by Google, its AI-powered security agent has uncovered more than 500 XSS vulnerabilities across its web applications since entering full operation in January. Google PageBreak uses Gemini models to autonomously investigate potential vulnerabilities, but reports them only after deterministic validators successfully reproduce the exploit against a running application, resulting in a near-zero false-positive rate. With PageBreak, every vulnerability hypothesis is test