# Google Discloses PageBreak AI Security Agent That Found 500+ XSS Bugs

DevFeed: [Google Discloses PageBreak AI Security Agent That Found 500+ XSS Bugs](<https://devfeed.tech/articles/google-discloses-pagebreak-ai-security-agent-that-found-500-xss-bugs-109652.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/10/google-pagebreak-security-agent/>)

Author: Renato Losio

Published: 2026-10-31T06:20:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [XSS](<https://devfeed.tech/topics/xss.md>), [Google](<https://devfeed.tech/topics/google.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-security](<https://devfeed.tech/tags/agentic-security.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-ml-data-engineering](<https://devfeed.tech/tags/ai-ml-data-engineering.md>), [ai-powered](<https://devfeed.tech/tags/ai-powered.md>), [ai-security](<https://devfeed.tech/tags/ai-security.md>), [ai-security-agent](<https://devfeed.tech/tags/ai-security-agent.md>), [application](<https://devfeed.tech/tags/application.md>), [applications](<https://devfeed.tech/tags/applications.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [cache](<https://devfeed.tech/tags/cache.md>), [codemender](<https://devfeed.tech/tags/codemender.md>), [development](<https://devfeed.tech/tags/development.md>), [devsecops](<https://devfeed.tech/tags/devsecops.md>), [exploit](<https://devfeed.tech/tags/exploit.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-models](<https://devfeed.tech/tags/gemini-models.md>), [google](<https://devfeed.tech/tags/google.md>), [google-pagebreak-security-agent](<https://devfeed.tech/tags/google-pagebreak-security-agent.md>), [information-security](<https://devfeed.tech/tags/information-security.md>), [ml-data-engineering](<https://devfeed.tech/tags/ml-data-engineering.md>), [news](<https://devfeed.tech/tags/news.md>), [security](<https://devfeed.tech/tags/security.md>), [security-vulnerabilities](<https://devfeed.tech/tags/security-vulnerabilities.md>), [vulnerabilities](<https://devfeed.tech/tags/vulnerabilities.md>), [web-applications](<https://devfeed.tech/tags/web-applications.md>), [xss](<https://devfeed.tech/tags/xss.md>)

## AI overview

Google says PageBreak found more than 500 XSS vulnerabilities across its web applications since entering full operation in January. The Gemini-powered agent investigates hypotheses, but reports a vulnerability to product teams only after a separate, engineer-written deterministic validator reproduces an exploit against a running application. Google says this keeps false positives near zero; unverified candidates are retained internally to guide future scans and validator development. The tradeoff is potential false negatives because validators do not cover every vulnerability type or complex scenario. PageBreak's reported effectiveness also draws on Google's monorepo visibility, signals linking live HTTP traffic to source code, and authenticated scanning infrastructure. Google is integrating it with CodeMender to generate fixes. The excerpt notes that the 500-plus findings have not been independently validated.

## Source excerpt

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