Claude published malicious code to the Internet and attacked 3 real companies

The intrusions happened through three Claude models: Opus 4.7, Mythos 5, and an internal research prototype. Opus 4.7, the ...

Hacking Scandals Are the New Humblebrag for AI Labs

AI hacking disclosures have fueled cybersecurity fears and calls for regulation. They're also the best marketing tool any lab ...

Anthropic’s Claude AI Broke Into Three Companies During Security Tests

Anthropic disclosed Thursday that three of its Claude models gained unauthorized access to the production systems of three organizations during cybersecurity testing.
Windows Report on MSN

Anthropic Says Claude Hacked 3 Organizations and Published Malicious PyPI Code

Anthropic says Claude models escaped security tests, published a malicious PyPI package, and accessed real production systems.
Cryptopolitan on MSN

Three Claude models broke into real companies during Anthropic cyber tests

Anthropic says three Claude models escaped sealed test environments and breached three real organizations after a ...
DATAQUEST

Anthropic review highlights security risks in AI cybersecurity evaluation environments

Anthropic says a review found Claude models accessed real-world systems after a third-party AI cybersecurity evaluation ...

After OpenAI, Anthropic admits its Claude AI models hacked into three real companies using…

Anthropic reviewed 141,006 of its own test runs after OpenAI's Hugging Face hack, and found three Claude models had broken ...
BeInCrypto

Anthropic Finds Claude Gained Unauthorized Access to 3 Organizations’ Systems

Anthropic says Claude models gained unauthorized access to 3 organizations' real systems in misconfigured cyber tests.
Virtualization Review

Now Claude AI Goes Rogue: 'One Older Model Continued Attacking'

Anthropic found three cybersecurity evaluation incidents in which Claude models gained unauthorized access to real organizations.

Anthropic’s Claude Thought the Internet Was a Simulation. Three Real Organisations Were Compromised

Anthropic revealed its Claude chatbot mistakenly accessed real-world systems during cybersecurity testing, leading to ...

Not just OpenAI: Now Anthropic says its internal models got online and cyberattacked 3 other organizations

Frontier AI systems are increasingly capable of translating narrowly defined objectives into complex, real-world cyber ...

Anthropic’s Claude escaped test sandbox to attack three organizations

Wrote and published malware during tests, which is apparently OK because leaky test environments were the real problem ...