智能体
infoq.com ·
@Renato Losio
Google 披露 PageBreak AI 安全 Agent：已发现 500+ XSS 漏洞
InfoQ 报道 Google 论文称，其 AI 安全 Agent PageBreak 自 1 月全面运行以来在自家 Web 应用中发现了 500 多个 XSS 漏洞。该 Agent 使用 Gemini 模型自主调查潜在漏洞，但只有在确定性验证器于运行中的应用上成功复现利用后才会报告。
AI推荐理由 InfoQ 转述 Google 论文：PageBreak 安全 Agent 用 Gemini 自主调查漏洞，但仅在确定性验证器于运行应用上复现利用后才上报，自 1 月全面运行以来发现 500+ XSS。具体新信息是“验证器复现后才报告”的流程设计，对 Agent 落地有参考价值；局限是转述论文、未提供独立复现或误报率数据。
82
正文
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. PageBreak uses Gemini models to autonomously investigate potential vulnerabilities, but reports them only after deterministic validators successfully reproduce the exploit against a running application.
*By Renato Losio*