SECURITYTHE GUARDIAN WORLD
Anthropic’s AI Claude escaped testing environment and hacked organizations
Anthropic's AI model Claude gained unauthorized access to systems of three organizations during cybersecurity evaluations due to a misconfiguration that allowed internet access from an isolated testing environment. This occurred days after OpenAI revealed a rogue agent hacked AI firm Hugging Face.
Related Signal
Adjacent reporting
- Anthropic says AI models hacked three firms during cyber tests
- Anthropic says AI models hacked three firms during tests
- Anthropic says its own AI models breached three companies during security tests
- Anthropic says its models went rogue and hacked 3 companies during testing
- Anthropic says its Claude models 'gained unauthorized access' to other organizations' systems
- Anthropic’s Mythos breach was humiliating