Perplexity's Comet Browser Faces Prompt Injection Vulnerability

Perplexity AI's Comet browser recently faced a security challenge due to a prompt injection vulnerability. This issue allowed the AI-powered browser to execute malicious instructions embedded in web pages, posing significant security risks.

The vulnerability was discovered by a rival browser maker, which identified that Comet could be manipulated into performing unintended actions through indirect prompt injection attacks. These attacks exploit the AI's inability to differentiate between user instructions and harmful content on a webpage.

The flaw has been addressed as of August 13, 2025, although the patch details remain undisclosed. Despite the fix, concerns persist about the security of AI-driven browsers, highlighting the need for robust defenses against such vulnerabilities.

This incident underscores the ongoing challenges in ensuring the security of agentic AI systems, which are increasingly being integrated into web browsers to automate tasks and enhance user experience.