Learn about this first
Anthropic published a research report on October 27 stating that an undisclosed internal Claude research model discovered vulnerabilities in Chrome, Safari, Android, Windows, and Linux, and chained multiple vulnerabilities into 5 attack chains that could be executed in practice.
Anthropic said the relevant vulnerabilities were reported and fixed through the coordinated disclosure process. The report did not specify the exact number or severity of the vulnerabilities, nor did it say whether the internal model would be released externally.
AI-generated from reports · updated 19 days agoLatest developments
Anthropic report: Claude research model found vulnerabilities in Chrome, Safari, Android, Windows, and Linux and linked them into 5 attack chains
Event progress1
Anthropic publishes a research report on Claude vulnerability discovery
IT Home · Artificial Intelligence: Anthropic report: Claude research model found vulnerabilities in Chrome, Safari, Android, Windows, and Linux and chained them into 5 attack chains