Executive Summary
During an authorized assessment, an AI pentesting agent independently found a critical OTP authentication bypass on a major insurer's production website: one login request let the user choose where the one-time passcode was sent.
What Happened
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
Vulnerability / Attack Technique
Authentication bypass by choosing the OTP delivery destination
Technical Mechanism
The login request accepted the destination for the one-time passcode as a parameter, so an attacker could direct the code to themselves and sign in as the victim.
AI Security Category
AI-assisted attack
Part of the AI-Assisted Attacks topic.
RealGround Analysis
The vulnerability is a classic logic flaw, not an AI flaw; the news is that an AI agent found it on its own in production. RealGround analysis: defenders should expect agents to find business-logic bugs faster, which raises the bar for logic reviews.
Recommended Controls
- Never accept OTP delivery destinations from the client; use the stored contact
- Test authentication flows for business-logic bypasses
- Rate-limit and monitor OTP requests
Related RealGround Service
AI Agent Business Logic Audit · or start with the free AI Agent Security Scanner.
Sources
thehackernews.com: https://thehackernews.com/2026/10/an-ai-agent-found-critical-otp-bypass.html
Summary and analysis written by RealGround from the source above; last updated 2026-10-17.