AI Workflows

“Identity Hijacking” of AI Workflows Can Expose Sensitive Internal Information to Attackers With a Simple Request

September 11, 2026

As documented by researchers with Noma Labs, a new attack on organizational AI workflows can provide attackers with sensitive internal information via nothing more than a polite request to their public-facing AI agent.

AI Workflows

“Identity Hijacking” of AI Workflows Can Expose Sensitive Internal Information to Attackers With a Simple Request

“Identity Hijacking” of AI Workflows Can Expose Sensitive Internal Information to Attackers With a Simple Request

Data Breach Hits Medical Supply Chain Giant McKesson, Exposing 284 Million Patient Records

Over 153 Million Drivers’ Licenses Offered on Dark Web After Identity Verification Company Breach

Cyber Attack at Three UK Airports Leaks PII of 8.7 Million Customers