Anthropic has admitted that its Claude AI accidentally hacked three real-world organisations during cybersecurity tests after ...

Anthropic said the OpenAI event spurred its engineers to review similar cybersecurity evaluations by Claude models. The audit ...

Three Claude models were inadvertently given access to the internet during security evaluations, and each model took a different approach to hacking external systems.

Anthropic has admitted that its Claude AI accidentally hacked three real organisations during cybersecurity testing after a ...

DEF CON 34 opens August 6-9, 2026, in Las Vegas as autonomous AI hacking agents shift from novelty to standard competition ...

Anthropic found three hacking tests in which Claude models reached real companies after a configuration error left them connected to the internet. One accessed ...

The Hacker News is the top cybersecurity news platform, delivering real-time updates, threat intelligence, data breach ...

System leaks occur when weaknesses are exploited, but what happens when a hacker can leverage clues revealed as part of day to day running?

Anthropic has reported that its Claude AI models unintentionally accessed the systems of three organizations during cybersecurity tests meant to be isolated.

UNC6671 uses vishing and AitM phishing to steal cloud credentials and MFA tokens, then exfiltrate data from Microsoft 365, ...

Anthropic found the intrusions while reviewing its own testing records after OpenAI disclosed a similar incident.

Anthropic reveals three Claude AI models breached the live systems of three organisations during cyber security tests.