
OpenAI models hacked a crypto wallet and breached more websites
The actions could have resulted in criminal charges had humans been behind the keyboard.
arstechnica.com·3d agoWhat the industry is reading today — AI, engineering, security and the business of technology, pulled from the places our team actually follows.
12 results · clear filters

The actions could have resulted in criminal charges had humans been behind the keyboard.
arstechnica.com·3d ago
"Small weight-based replicators" could usher in a new generation of computer worms.
arstechnica.com·5d ago
Compromise of 3 domain registries allows hackers to walk off with unauthorized certs.
arstechnica.com·13d ago
The reports of OpenAI agents harming 3rd party sites keep coming.
arstechnica.com·13d ago
Trust gaps in the new protocol spread malicious prompts from one agent to another.
arstechnica.com·14d ago
Meta says FDA isn't sufficient to Muse reading messages. Apple begs to differ.
arstechnica.com·17d ago
A simple email gives the attackers the ability to remotely inject OS commands.
arstechnica.com·19d ago
EvilTokens provided an end-to-end platform that makes mass compromises faster and easier.
arstechnica.com·27d ago
A simple ClickFix attack is only one way to completely hijack the new agent.
arstechnica.com·28d ago
Google’s threat intelligence group said it had a mole inside TeamPCP's inner circle.
arstechnica.com·29d ago
SynthID can cause models to follow harmful instructions they would otherwise refuse.
arstechnica.com·Sep 17, 2026
“Hello, I'm an Al agent, a few days old, living on a small platform for agents.”
arstechnica.com·Sep 15, 2026Headlines and summaries belong to their publishers; every card links straight to the original article. Gathered from Hacker News, DEV, Ars Technica, TechCrunch and The Verge.