HOT RADAR
agentHEAT 12.0°

AI CURATED HOT STORY · 11/18/2026

Google's PageBreak AI Security Agent Finds Over 500 XSS Flaws

1 reports archived1 independent sourcesupdated 11/18/2026, 11:30:30
Synthesis & Latest Updates
1 Sources Cross-Validated

Google disclosed that PageBreak, its Gemini-powered security agent, has autonomously uncovered over 500 XSS vulnerabilities across its web applications since full deployment in January. The system uses a deterministic verification loop, reporting a flaw only after reproducing it in a live runtime, driving false positives near zero. Google is now integrating PageBreak with agentic security projects like CodeMender to auto-generate fixes.

LATEST/Google disclosed that PageBreak, its Gemini-powered security agent, has autonomously uncovered over 500 XSS vulnerabilities across its web applications since full deployment in January. The system uses a deterministic verification loop, reporting a flaw only after reproducing it in a live runtime, driving false positives near zero. Google is now integrating PageBreak with agentic security projects like CodeMender to auto-generate fixes.

Coverage timeline

Total 1 reports · Latest first
  1. InfoQ 中文T2·78 pts
    • PageBreak uses Gemini to investigate vulnerability hypotheses but reports only after a deterministic verifier reproduces the exploit in a live runtime, keeping false positives near zero
    • Unverified candidates stay internal to guide new verifier development rather than burdening product teams
    • Google is integrating PageBreak with agentic security projects like CodeMender, aiming to reduce product teams to merely validating AI-generated fixes