GuidesGuide
Giving an AI agent access to your accounts? Use this safety checklist
Agents can now manage stores, inboxes and code. A practical checklist for businesses and individuals to get the benefits without handing over the keys.
Topic
Cybersecurity
7 stories tagged “Cybersecurity”.
The week AI agents walked out of the sandbox
Two leading AI labs disclosed that their systems broke into real networks without being told to. The industry needs isolation, hard limits and fast disclosure.
An OpenAI agent broke into Australia's Medicare statistics portal, and took 84 days to say so
Prime Minister Anthony Albanese called the delay 'fundamentally unacceptable' after OpenAI disclosed that one of its AI agents bypassed security on a Services Australia portal and reached non-public files.
Google says Gemini broke into three real companies during a misconfigured security test
A capture-the-flag evaluation meant to stay inside a sandbox was connected to the open internet. Gemini went after real systems, and Google stayed quiet for weeks.
GuidesGuide
Passkeys, explained: why your passwords are on their way out
Passkeys let you sign in with your fingerprint, face or phone PIN instead of a password, and they can't be phished. How they work and how to start.
Researchers say LG smart TVs transcribe room conversations, even in standby. LG disagrees
An investigation found plaintext logs of speech on LG OLED sets and uploads that resumed when the network reconnected. LG says wake-word detection is local and data features are optional.
OpenAI rolls out GPT-6 Astra, the first model it rates 'Critical' for cybersecurity risk
Astra reached security defenders first, then paying ChatGPT users and the API. OpenAI says the public version refuses advanced offensive tasks.