Malicious Chromium extension impersonates Perplexity AI to hijack browser searches and collect data
By
Microsoft Defender Security Research Team
Summary
Microsoft Threat Intelligence has identified a malicious Chromium-based browser extension that impersonates the AI-powered answer engine Perplexity AI. The extension's primary goal is to intercept browser search traffic and collect user data, potentially enabling profiling, targeted advertising, or other misuse. The extension uses Manifest V3 APIs and intermediary infrastructure to redirect searches. Microsoft responsibly disclosed the threat to Google, and the extension has been taken down.
Source
Key quotes
· 3 pulledMicrosoft Threat Intelligence has identified a malicious Chromium-based extension that spoofs the AI-powered answer engine Perplexity AI to trick unsuspecting users into installing it.
Based on our observation of the extension's behavior, we assess its primary objective to be search traffic interception and data collection, which might enable downstream use cases such as profiling, targeted advertising, or other forms of misuse depending on operator intent.
Through responsible disclosure, we reported this extension to Google, and it has been taken down as of this writing.
You might also wanna read
Malicious Perplexity Chrome Extension Intercepted Searches and Address Bar Input
Critique of AI Browser Proliferation: Chromium-Based Browsers with AI Features
The article critiques the recent trend of AI browsers being announced by companies like OpenAI (Atlas), Perplexity (Comet), and others, argu
Security Researchers Discover Indirect Prompt Injection Vulnerability in Perplexity Comet AI Browser
Brave security researchers discovered a critical vulnerability called "indirect prompt injection" in Perplexity Comet, an AI-powered browser
AI-Generated Browser Ransomware Abuses Chromium API on Windows, Linux, macOS, Android
Perplexity AI Accused of Using Stealth Crawlers to Bypass No-Crawl Directives
Perplexity, an AI-powered answer engine, is reportedly using stealth tactics to bypass website no-crawl directives. Evidence suggests the co
Security Vulnerabilities in Agentic AI Browsers: Testing Reveals Scam Susceptibility
The article examines the emerging security vulnerabilities in agentic AI browsers that autonomously browse, search, and interact online. It

Comments
Sign in to join the conversation.
No comments yet. Be the first.