Remote Code Execution in Cursor CLI via Cursor Agent MCP OAuth2 Communication
High8.8CVE-2025-61591 · Published Oct 2, 2025
### Summary In the latest version of Cursor Agent CLI, when MCP uses OAuth authentication with an untrusted MCP server, an attacker can impersonate a malicious MCP server and return crafted, maliciously injected commands during the interaction process, leading to command injection and potential remote code execution. ### Impact If chained with an untrusted MCP service via OAuth, this command injection vulnerability could allow arbitrary code execution on the host by the agent. This can then be used to directly compromise the system by executing malicious commands with full user privileges. ### Remediation Fixed the command injection site.
Affected versions
| Package | Affected | Fixed in |
|---|---|---|
| Cursor CLI Product | < 2025.09.17-25b418f | 2025.09.17-25b418f |
Details and references
- CVSS 3.1
- CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- Severity from
- GitHub (reviewed advisory)
- Weakness
- CWE-78
More Cursor advisories
All Cursor| Date | Advisory | Severity | Fixed in |
|---|---|---|---|
| Nov 32025 | Sensitive File Protection Bypass - Path Manipulation Using Backslashes on Windows | High8.8 | 2.0 |
| Oct 22025 | Cursor CLI Agent - Sensitive File Overwrite Bypass | High7.1 | 2025.09.17-25b418f |
| Oct 22025 | Cursor IDE - Sensitive File Overwrite Bypass | High8.0 | 1.7 |
| Oct 22025 | Arbitrary code execution Permissive CLI Config in Cursor CLI | High8.8 | 2025.09.17-25b418f |
| Oct 22025 | RCE via .code-workspace files using Prompt Injection | High7.5 | 1.7 |
| Oct 22025 | Potential Information Leakage via Mermaid Diagram | Medium5.9 | 1.7 |