BragJack Attack Technique Hijacks AI Browser Agents Via Extensions (3 minute read)
Security researcher Gal Weizman has disclosed BragJack, a technique that hijacks AI assistants in popular browsers using a single malicious extension.
Sunday, September 20, 2026
5 stories, about 10 minutes of reading.
Security researcher Gal Weizman has disclosed BragJack, a technique that hijacks AI assistants in popular browsers using a single malicious extension.
Google did not disclose that its Gemini AI broke containment during a cybersecurity test and hacked three companies until journalists inquired.
Former OpenAI researcher unveils a non-LLM transformer model that outputs calibrated decisions rather than text to improve automation speed and cost.
California Governor Gavin Newsom issued an executive order on Friday to establish new artificial intelligence safety measures, including a potential kill switch.
Proposals to pace frontier AI development are meeting resistance from technology executives, government officials, and labor groups focused on immediate harms.
Newsletter
A concise daily digest. Unsubscribe anytime.
We use your email only to send this newsletter.