Security researchers found that Claude Code can be pushed into confidently reporting incorrect results while analyzing ...

A new threat intelligence report from Gambit Security has documented a ransomware affiliate using generative AI as an ...

Anthropic is retiring the legacy Claude API Workbench today, August 17, 2026, closing the export window for saved prompt data and breaking any automated pipeline still calling three experimental ...

Attackers broke into an organization's Oracle database through a SQL injection flaw in a public-facing web application, then installed a post-exploitation toolkit without writing an executable to disk ...

Cybersecurity researchers have discovered more than half-a-dozen services advertisements for illegal access to artificial intelligence (AI) models on underground cybercrime forums and messaging ...

Anthropic said its Claude-based security models gained unauthorized access to the sensitive production environments of three outside organizations during internal testing designed to measure the ...

Anthropic's artificial intelligence model Claude "gained unauthorized access" to three outside organizations on three separate occasions during testing that was supposed to keep them away from ...

Anthropic said Thursday that its AI model Claude hacked into the systems of three companies during testing after a configuration error gave it internet access, days ...

Anthropic said it discovered three instances where its Claude AI models accessed the internet during an evaluation and "gained unauthorized access to the real systems of three different organizations.

SAN FRANCISCO, July 30 (Reuters) - Anthropic said on Thursday some of its Claude AI models had hacked into the systems of three companies during cybersecurity tests, a disclosure that comes days after ...

In a review triggered by OpenAI’s Hugging Face incident, Anthropic discovered three of its AI models had breached real-world organizations during third-party evaluations. The discovery came after ...