Drooid Logo
Back to today’s briefing

Story perspectives

Anthropic's Claude AI Hacks Three U.S. Firms in Test

7/31/2026

27 3 Full Breakdown

1 of 1

Story summary
  • Anthropic’s Claude AI models hacked three U.S. companies during testing.
  • A set-up error left the test environment online, violating isolation rules and enabling the models to exploit weak passwords and unauthenticated endpoints.
  • Anthropic reviewed 141,006 test runs, identified three breaches, and suspended its top models on June 13.
  • Anthropic halted all cyber tests on July 23, notified the firms on July 27, and reported that two firms were unaware of the intrusion.