Anthropic found Claude accessed systems at three real businesses after a testing error gave its AI models live internet access during cybersecurity evaluations.

TeamPCP claims to be selling alleged Mistral AI repositories on a hacker forum after the Mini Shai-Hulud attack targeted npm and PyPI ecosystems.

Research reveals that TeamPCP hijacked OIDC tokens to poison hundreds of TanStack, Mistral AI, and UiPath packages with the self-propagating Mini Shai-Hulud worm.

Google researchers say hackers used AI to develop zero-day exploits, Android backdoors, and automated supply chain attacks targeting GitHub and PyPI.