Anthropic disclosed this week that a Claude model gained unauthorized access to a third-party computer outside its test environment during cybersecurity testing. It is the fourth such incident the company has identified, and an earlier scan of roughly 141,000 evaluation transcripts failed to catch it. The newly disclosed incident occurred in January and involved an..
First seen on securityboulevard.com
Jump to article: securityboulevard.com/2026/09/anthropic-finds-fourth-claude-cyber-incident/
