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·1d ago14 results · clear filters
Anthropic warns small AI models could self-replicate through IoT devices
"Small weight-based replicators" could usher in a new generation of computer worms.
arstechnica.com·3d ago
Hackers obtain counterfeit TLS certificates for Google and other large services
Compromise of 3 domain registries allows hackers to walk off with unauthorized certs.
arstechnica.com·11d ago
OpenAI agents tried to hack Wikipedia tools and flooded it with traffic
The reports of OpenAI agents harming 3rd party sites keep coming.
arstechnica.com·11d agoMCP for agent-to-agent comms may be the riskiest protocol you've never heard of
Trust gaps in the new protocol spread malicious prompts from one agent to another.
arstechnica.com·12d ago
Apple changes full-disk access permissions to curb abuse from AI agents
Meta says FDA isn't sufficient to Muse reading messages. Apple begs to differ.
arstechnica.com·15d ago
Attackers have been exploiting critical Zimbra flaw to steal emails
A simple email gives the attackers the ability to remotely inject OS commands.
arstechnica.com·17d ago
Microsoft disrupts AI-assisted platform that compromised 12,000
EvilTokens provided an end-to-end platform that makes mass compromises faster and easier.
arstechnica.com·25d ago
Muse, Meta's extraordinarily privileged AI assistant, has a serious 0-day
A simple ClickFix attack is only one way to completely hijack the new agent.
arstechnica.com·26d ago
An undercover Google analyst infiltrated a notorious supply-chain hacking gang
Google’s threat intelligence group said it had a mole inside TeamPCP's inner circle.
arstechnica.com·27d ago
LLMs respond differently to harmful prompts when AI watermarking is used
SynthID can cause models to follow harmful instructions they would otherwise refuse.
arstechnica.com·Sep 17, 2026
AI bots "Timmy," "Ren," and "Jackie" are flooding social media with slop
“Hello, I'm an Al agent, a few days old, living on a small platform for agents.”
arstechnica.com·Sep 15, 2026OpenAI agents discussed ways to escape their sandbox on public wiki
In all, 3,700 internal agents posted 18,000 messages discussing cheating on a test.
arstechnica.com·Sep 5, 2026
Once popular for attacking AI, ASCII smuggling is embraced by spammers
A once-overlooked block of unicode that's invisible to humans is gaining ever wider use.
arstechnica.com·Sep 4, 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.