Setup Error Let Models Steal Data and Release Malware Online. Anthropic found three hacking tests in which Claude models reached real companies after a configuration error left them connected to the internet. One accessed customer data, another released malware that ran on 15 computers and a third scanned 9,000 systems.
First seen on govinfosecurity.com
Jump to article: www.govinfosecurity.com/anthropic-ai-models-hacked-3-real-companies-a-32384
