Your AI browser can be hijacked by prompt injection, OpenAI just patched Atlas

OpenAI says it has patched ChatGPT Atlas after internal red teaming found new prompt injection attacks that can hijack AI ...

WebRAT malware spread via fake vulnerability exploits on GitHub

The WebRAT malware is now being distributed through GitHub repositories that claim to host proof-of-concept exploits for ...
GlobalData on MSN

Lantmännen to snap up Italy’s Panificio San Francesco

Magnus Kagevik, group president and CEO of Lantmännen said: "The agreement in Italy reflects our ambition to build a strong ...

How OpenAI is defending ChatGPT Atlas from attacks now - and why safety's not guaranteed

An 'automated attacker' mimics the actions of human hackers to test the browser's defenses against prompt injection attacks. But there's a catch.

CASI Pharmaceuticals Receives Extension from Nasdaq to Meet Listing Requirements

SOUTH SAN FRANCISCO, CALIFORNIA / ACCESS Newswire / December 23, 2025 / CASI Pharmaceuticals, Inc. (NASDAQ:CASI), a clinical-stage biopharmaceutical company focused on developing CID-103, a potential ...

OpenAI Says Prompt Injections a Challenge for AI Browsers, Builds an Attacker to Train ChatGPT Atlas

OpenAI says prompt injections remain a key risk for AI browsers and is using an AI attacker to train ChatGPT Atlas.
WinBuzzer

OpenAI Deploys Automated ‘Attacker’ to Harden Atlas Browser, Admits Prompt Injection Is ‘Unsolved’

OpenAI has deployed a new automated security testing system for ChatGPT Atlas, but has also conceded that prompt injection ...