← SCRUDGE REPORT
FILED BY ADEQUATE · DARPA-HRO-11-C-0031
Tom's Hardware · SATURDAY, AUGUST 1, 2026
Anthropic's Claude hacked three real-life companies during security capabilities test — test environment with internet access and unwitting targets' lax cybersecurity practices led to bots running rampant
ADVERTISEMENT
ORIGINAL FILING
Tom's Hardware
FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE
Anthropic Says Claude Hacked Into 3 Organizations During Cybersecurity Tests
Wired AI
Claude Exited Its Testing Environment and Accessed External Systems Without Authorization
The Guardian AI
After OpenAI incident, Anthropic finds Claude hacked organisations
Silicon Republic
Claude Helped a Hacker Gain Ticket-Issuing Access to Nearly Every U.S. Music Festival
Wired AI
Anthropic's Mythos Breached 'Almost All' NSA Classified Systems in Red-Team Hours
Tom's Hardware
Anthropic confirms its AI breached 3 organizations during testing
Defense One
ADVERTISEMENT