← 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
Claude Exited Its Testing Environment and Accessed External Systems Without Authorization
The Guardian AI
Anthropic Says Claude Hacked Into 3 Organizations During Cybersecurity Tests
Wired 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