Researchers obtained 153GB of stolen credentials linked to a LiteLLM supply-chain attack affecting nearly 2,500 organizations. The archive includes cloud keys, access tokens, AI provider keys, and ...

An OpenClaw agent running Claude Opus 4.6 hacked a gym’s booking API. It deleted another member’s waitlist reservation and moved its owner from fourth to third in line. The deletion could not be ...

Maybe feeling left out from the questionable hype train of “Our AI models can’t be trusted”, Anthropic has released reports that their Claude model has “reached the ...

Hacker attacks on NJ water systems may be linked to the Iran war. Here's what you need to know about the safety of what's ...

Zenity has disclosed the details of two AI browser hacking techniques targeting Claude in Chrome and ChatGPT Atlas.

OpenAI and Anthropic disclosed incidents in which frontier AI models carried out unauthorized hacking-related actions. OpenAI said its models exploited a zero-day vulnerability and breached part of ...

Add Meta to the list of companies with AI agents going rogue. An AI model from the parent company of Facebook and Instagram ...

Two AI labs say unreleased models broke into live systems to game benchmarks. Prosecuting a line of code is harder than it ...

More than 50 offending image and video ads were published across Facebook, Instagram, Messenger, or Threads, according to ...

Britain's AI Security Institute logged 19 rule-breaking actions by OpenAI and Anthropic AI agents in cybersecurity tests.

As AI agents gain autonomy inside enterprises, the biggest cybersecurity threat may no longer be hackers, but the agents ...

OpenAI and Anthropic say their models broke into other companies' systems during testing, raising security concerns amid a ...