Skip to main content
Mallory
← Back to News
internet-facing-service-vulnerabilityendpoint-software-vulnerability

Google's PageBreak AI Agent Finds More Than 500 Verified XSS Vulnerabilities

Vulnerability Disclosure · 4 sources · Updated 2mo ago · First seen Oct 5, 2026

Google's PageBreak AI Agent Finds More Than 500 Verified XSS Vulnerabilities

Google reported that PageBreak, its internal AI security agent primarily powered by Gemini models, discovered more than 500 verified cross-site scripting (XSS) vulnerabilities across its first-party web applications. The agent combines LLM-driven discovery with deterministic validators that execute real exploit payloads before escalating findings to engineers, producing what Google describes as a near-zero false-positive rate. Notable discoveries included JavaScript cache poisoning, an administrative-console exploit chain that bypassed signature-based protection, and universal XSS involving the Tag Assistant Extension. The activity was defensive testing, not a confirmed intrusion; Google found no evidence of attacker exploitation of the cache-poisoning flaw.

PageBreak's validators cover XSS, SQL injection, path traversal, remote code execution, and server-side request forgery, although incomplete validators can miss genuine vulnerabilities. As of September 4, Google reported only two XSS issues among hundreds of applications using its high-assurance web frameworks, both confined to internal applications or debug endpoints with hardening gaps. Google plans closer integration with automated remediation initiatives, including CodeMender, while retaining engineer review of proposed fixes. The findings reinforce the value of verified exploit evidence and secure-by-design frameworks, rather than relying on unvalidated AI findings alone.

Do you run this?See affected versions and whether adversaries are exploiting it.
Check your exposure
Event timeline

How this story unfolded

Events from the most recent confirmed update back to the earliest known activity.

7 events · Nov 2025 – Jan 2026
  1. Reported Oct 5, 20262mo ago

    PageBreak discovers universal XSS involving the Tag Assistant Extension

    PageBreak demonstrated an exploit chain combining weak external-connection checks, recovery of a one-time nonce, and unsafe message forwarding in the Tag Assistant Extension. Support for data URLs enabled attacker-controlled JavaScript to execute on a page under debugging.

    Google’s AI Hacker Finds 500+ XSS Flaws and Builds Working Exploit Chains | Cryptika Cybersecurity
  2. Reported Oct 5, 20262mo ago

    PageBreak demonstrates a signed-redirect XSS chain in Google's admin console

    PageBreak identified an XSS chain at admin.google.com involving an unsafe redirect in /a/autodns/registrar. It found that /a/autodns/authorize could generate a valid signature for a malicious JavaScript URI, overcoming the signature protection that initially prevented exploitation.

    Google’s AI Hacker Finds 500+ XSS Flaws and Builds Working Exploit Chains | Cryptika Cybersecurity
  3. Reported Oct 5, 20262mo ago

    PageBreak discovers JavaScript cache poisoning at apis.google.com

    PageBreak discovered that an unchecked URL path segment entered returned JavaScript but was excluded from the cache key, allowing poisoned responses to reach other visitors in the same geographic area. The flaw could have enabled XSS on Google domains and external sites loading the script; Google found no evidence of attacker exploitation.

    Google’s AI Hacker Finds 500+ XSS Flaws and Builds Working Exploit Chains | Cryptika Cybersecurity
  4. Reported Sep 24, 20262mo ago

    Google reports more than 500 verified XSS discoveries by PageBreak

    Google reported that PageBreak had discovered more than 500 verified XSS vulnerabilities across its first-party web applications, including sensitive domains. Findings were validated through real payload execution before escalation to product teams.

    Agentic Hacks, Real Proofs: Inside Google's PageBreak Project
  5. Reported Sep 24, 20262mo ago

    PageBreak identifies two XSS flaws in high-assurance-framework applications

    As of September 4, 2026, PageBreak had identified two XSS vulnerabilities among hundreds of applications built with Google's high-assurance web frameworks. Both affected internal applications or debug endpoints with hardening gaps; the individual discovery dates were not stated.

    Agentic Hacks, Real Proofs: Inside Google's PageBreak Project
  6. Jan 2026

    PageBreak becomes a full project

    Google expanded PageBreak from a pilot into a fully fledged project focused on scaling vulnerability discovery and reducing manual triage through deterministic exploit validation.

    Agentic Hacks, Real Proofs: Inside Google's PageBreak Project
  7. Nov 2025

    Google launches PageBreak pilot

    Google Product Security began piloting PageBreak, an internal AI agent for discovering and validating vulnerabilities in Google's first-party web applications.

    Agentic Hacks, Real Proofs: Inside Google's PageBreak Project
Linked entities

Related entities

Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.

Open in app →

Organizations

1 linked
Google
Do you run this?See whether adversaries are exploiting this yet, and where the affected versions run in your environment.
Check Your Exposure
Mallory platform

See the full picture, correlated to your attack surface.

This page covers what’s public. Mallory adds the parts that aren’t: which of your assets are affected, which threat actors are using it right now, and what to deploy next.

Exposure mappingMap indicators from this story to your assets and identify affected systems in minutes.
Threat actor evidenceEvery observed campaign, victim, and pivot linked to actors named in this story.
Associated malwareMalware, exploits, and IOCs connected to the activity described here.
Detection signaturesYARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Scheduled alertsGet matching new stories delivered to your team as they break, not the next morning.
AI threadsAsk questions about this story and take action on the answers.