A Flaw in ChatGPT’s Mac App Could Have Let Hackers Grab Sensitive Data
While the focus has been on AI agents’ hacking capabilities, a recently patched vulnerability in a ChatGPT app shows that AI software is itself an inviting—and vulnerable—target.
Get smart on it
A recently patched vulnerability in the macOS version of ChatGPT could have allowed attackers to take over the app on a victim's computer and access all stored chat logs and data, as well as browser sessions and other interconnected information. The flaw was discovered by researchers at the Objective-See Foundation and exploited a weakness in how the app's components verified each other's authenticity through digital signatures. AI software has become an appealing target for attackers because these platforms require deep system access and high levels of trust to function effectively, making compromises particularly damaging. The vulnerability was relatively simple to exploit and highlights concerns that security may be an afterthought as AI companies prioritize adding features.
Related news
These AI Experts Want to Do High-Stakes Research Out in the Open
Many frontier labs keep their risky research locked away. Trillium Labs wants to show off its work when it comes to self-improvement and model behavior.
Trump’s Crazy AI Rebrand Was a Loyalty Test for Tech Execs, and It Worked
For years these billionaires gushed obsessively about AI. But they meekly went along when Trump cancelled the term.
