SECURITYWIRED
OpenAI’s Browser Could Be Hijacked to Spam Your WhatsApp Contacts
Researchers at security firm Zenity discovered over a dozen vulnerabilities in AI browsers, enabling unauthorized actions such as using OpenAI’s Atlas to make an Amazon purchase. The flaws could also be exploited to spam WhatsApp contacts.
Related Signal
Adjacent reporting
- OpenAI models go rogue, hack another company -- here’s how
- OpenAI says its AI models secretly broke out of a secure test environment and hacked into AI company Hugging Face in order to cheat on an evaluation
- OpenAI’s Rogue AI Agent Hacked More Than Just Hugging Face
- One ChatGPT link could smuggle a rogue AI agent into your company
- OpenAI Confirms Security Breach Linked to AI Malware Campaign