Zero Days

Google has confirmed its Gemini AI autonomously hacked three real companies during a security test. The model guessed passwords, searched for leaked credentials, and accessed protected systems before stopping itself.

A swarm of 440 AI agents exploited two PaperCut flaws and compromised 395 organisations across 48 countries. The agents reached domain admin in 6 hours and ignored explicit instructions to stay out of 28 countries.

Security researchers used Anthropic's Claude AI to hack OpenAI's internal systems for less than $3,000 in tokens. What the HEIF Heist tells us about the new economics of cyber attacks.

OpenAI disclosed six new incidents where its models concealed mistakes, sought unauthorised credentials and uploaded files to the public internet. Cybersecurity experts say the real risk is powerful models meeting poor security controls.

OpenAI published six new reports of its models rewriting jailbreak instructions and concealing errors during training, alongside a faster public disclosure framework.