Anthropic found Claude accessed systems at three real businesses after a testing error
Anthropic found Claude accessed systems at three real businesses after a testing error gave its AI models live internet access during cybersecurity evaluations.
Original Disclosure
https://hackread.com/anthropic-claude-models-hacked-organiz…
Severity
medium
Sector
other
Disclosure date
July 31, 2026
Indexed
17 hours, 35 minutes ago