Cursor CVE-2025-64109
HIGHSeverity by source
AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Primary rating from GitHub Advisory · only source for this CVE.
CVSS VectorGitHub Advisory
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Lifecycle Timeline
2DescriptionGitHub Advisory
Cursor is a code editor built for programming with AI. In versions and below, a vulnerability in the Cursor CLI Beta allowed an attacker to achieve remote code execution through the MCP (Model Context Protocol) server mechanism by uploading a malicious MCP configuration in .cursor/mcp.json file in a GitHub repository. Once a victim clones the project and opens it using Cursor CLI, the command to run the malicious MCP server is immediately executed without any warning, leading to potential code execution as soon as the command runs. This issue is fixed in version 2025.09.17-25b418f.
AnalysisAI
Cursor is a code editor built for programming with AI. Rated high severity (CVSS 8.8), this vulnerability is remotely exploitable, no authentication required, low attack complexity. No vendor patch available.
Technical ContextAI
This vulnerability is classified as OS Command Injection (CWE-78), which allows attackers to execute arbitrary operating system commands on the host. Cursor is a code editor built for programming with AI. In versions and below, a vulnerability in the Cursor CLI Beta allowed an attacker to achieve remote code execution through the MCP (Model Context Protocol) server mechanism by uploading a malicious MCP configuration in .cursor/mcp.json file in a GitHub repository. Once a victim clones the project and opens it using Cursor CLI, the command to run the malicious MCP server is immediately executed without any warning, leading to potential code execution as soon as the command runs. This issue is fixed in version 2025.09.17-25b418f. Version information: version 2025.09.17.
Affected ProductsAI
See vendor advisory for affected versions.
RemediationAI
No vendor patch is available at time of analysis. Monitor vendor advisories for updates. Avoid passing user input to shell commands. Use language-specific APIs instead of shell execution. Apply strict input validation with allowlists.
Same weakness CWE-78 – OS Command Injection
View allSame technique Command Injection
View allShare
External POC / Exploit Code
Leaving vuln.today