Agentic browsers face significant security risks, such as prompt injection, but early defenses demonstrate why security will be the true differentiator.
Claude for Chrome (now in pilot), Perplexity’s Comet, and Dia are all pushing the idea of a browser that doesn’t just display pages but acts within them. But as soon as you let an AI click, type, and execute, the hardest problem comes into view: security. The quiet threat of prompt injection Anthropic deserves credit for going deep on vulnerabilities in its Claude for Chrome pilot. “Some vulnerabilities remain to be fixed before we can...
Read more →