Advertisement

research

Researchers at Zenity Labs discovered flaws affecting multiple AI browsers, including Perplexity’s Comet. Before being patched, an attacker could exploit them via a legitimate calendar invite, using a prompt injection to force the AI browser to act against its user. (Image via Getty)

Researchers discover suite of agentic AI browser vulnerabilities

Through a simple calendar invite, AI browsers like Comet can be directed to access local file systems, browse directories, open and read files, and exfiltrate data.
Advertisement
This photograph taken on January 13, 2025 in Toulouse shows screens displaying the logo of Grok, a generative artificial intelligence chatbot developed by xAI, the American company specializing in artificial intelligence and it’s founder South African businessman Elon Musk. (Photo by Lionel BONAVENTURE / AFP) (Photo by LIONEL BONAVENTURE/AFP via Getty Images)

Why skipping security prompting on Grok’s newest model is a huge mistake

An AI red-teaming company found that xAI’s Grok 4 is “not suitable for enterprises” without substantial security prompting. 
Advertisement
Advertisement
Advertisement