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

The bug was simple: the login let you choose where your sign-in code went. Proving it on a live website was the hard part. TL;DR During an authorized assessment, an AI pentesting agent found a critical authentication bypass on a major insurer's production website, on its own. One login request let the user choose where the one-time passcode went. The attack was the easy part. Proving it

During an authorized assessment, an AI pentesting agent independently identified a critical OTP authentication bypass on a major insurer’s production website: the login flow allowed the requested delivery channel and address to be changed, sending the code to an attacker-controlled inbox.[1] The agent stopped after confirming successful login, and the issue was reported to the insurer.[1] RealGround analysis: AI agents operating against production systems require strict authorization boundaries, guardrails, and business-logic testing to prevent harmful validation activity; the underlying flaw also warrants server-side binding of OTP delivery to the registered account.