Cursor is a code editor built for programming with AI. In versions 1.2.4 and below, attackers can achieve remote and persistent code execution by modifying an already trusted MCP configuration file inside a shared GitHub repository or editing the file locally on the target's machine. Once a collaborator accepts a harmless MCP, the attacker can silently swap it for a malicious command (e.g., calc.exe) without triggering any warning or re-prompt. If an attacker has write permissions on a user's active branches of a source repository that contains existing MCP servers the user has previously approved, or allows an attacker has arbitrary file-write locally, the attacker can achieve arbitrary code execution. This is fixed in version 1.3.
Published: 2025-08-06
Cursor AI Editor is vulnerable to code execution via two flaws in how it handles MCP servers named "CurXecute" and "MCPoison."
https://www.darkreading.com/vulnerabilities-threats/rce-flaw-ai-coding-tool-supply-chain-risk
https://thehackernews.com/2025/08/cursor-ai-code-editor-vulnerability.html
https://research.checkpoint.com/2025/cursor-vulnerability-mcpoison/
https://www.securityweek.com/several-vulnerabilities-patched-in-ai-code-editor-cursor/
Published: 2025-08-02
Updated: 2025-08-04
Named Vulnerability: MCPoison
Base Score: 8.3
Vector: CVSS2#AV:N/AC:L/Au:M/C:C/I:C/A:C
Severity: High
Base Score: 7.2
Vector: CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H
Severity: High
EPSS: 0.00067
Tenable Research has classified this CVE under the following Vulnerability Watch classification, which includes active and historical (inactive) classifications. You can learn more about these classifications on our blog.
Vulnerability Being Monitored