Rogue MCP Servers Exploit Vulnerability in Cursor's Internal Browser
Article Content
Browse articles
Hackers are exploiting a critical vulnerability in Cursor, an AI-powered code editor, by using compromised Model Context Protocol (MCP) servers to inject malicious code. This attack allows the rogue servers to manipulate Cursor's internal browser, potentially replacing legitimate login pages with attacker-controlled ones. The lack of integrity verification in Cursor's proprietary features makes it particularly susceptible to these attacks.
Ask AI about this cluster
Answers cite the sources they use
Updated 248d ago How this analysis works
More articles in this cluster (2)
Following this threat?
Track XWorm, Cursor and CVE-2025-64446 in your own feed — you're alerted when they show up in new reporting, leak sites or exploitation.
Free account · no card needed
Continue Reading
ClickFix Scams Target Education Sector and General Public ClickFix scams are increasingly targeting users in the UK, particularly within the education sector, as reported by Jisc and Jammu Kashmir Police. These scams manipulate users into executing malicious commands through fake CAPTCHA prompts and browser error messages. Jisc has blocked between 300 and 37,000 phishing…
Asymptote Labs Secures $5.5M for AI Agent Security Solutions Asymptote Labs has raised $5.5 million in seed funding to develop runtime security for enterprise AI agents. The funding will enhance product development and engineering efforts, addressing the monitoring gaps that security teams face with autonomous tools accessing sensitive data. Central to their approach is Beacon…