David Reynolds

Hacker used Anthropic’s Claude chatbot to attack multiple government agencies in Mexico

A hacker exploited Anthropic’s Claude chatbot to carry out attacks against Mexican government agencies, resulting in the theft of 150GB of official government data, including taxpayer records and employee credentials. The hacker used Claude to find vulnerabilities in government networks and automate data theft, with Gambit Security confirming the breach. Anthropic has investigated the claims, banned the accounts involved, and released a new model with tools to prevent misuse.

Read More