An AI Agent Found a Critical OTP Bypass in Production. The Attack Was the Easy Part.

Summary

During an authorized assessment, Reflectiz's AI pentesting agent found a critical authentication bypass on a major insurer's production website without human direction. The login OTP request accepted channel and address fields that let the code be sent to an arbitrary email address instead of the one registered to the account, and the server never checked that the address belonged to the account. The agent stopped after confirming login, and Reflectiz reported the flaw to the insurer.

Topics

• AI agents

Related items

• InfoResearchers Used a Public OpenAI Model to Build a $250,000 Chrome Full-Chain Exploit in Six DaysSimilar attack · The Hacker News
• LowFBI arrests Saudi OpenAI employee who allegedly planted recording device in conference roomSimilar attack · CNBC Technology
• MediumVisual Studio Copilot and SSMS Remote Code Execution (CVE-2026-103572)Similar attack · Embrace The Red
• LowAnthropic warns self-replicating AI could spread to your smart devicesSimilar attack · BleepingComputer
• HighCVE-2026-110207: Wukong AICRM missing authorization in user and role administration APIsSimilar attack · NVD/CVE Database