LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.74.2 to before version 1.83.7, two endpoints used to preview an MCP server before saving it — POST /mcp-rest/test/connection and POST /mcp-rest/test/tools/list — accepted a full server configuration in the request body, including the command, args, and env fields used by the stdio transport. When called with a stdio configuration, the endpoints attempted to connect, which spawned the supplied command as a subprocess on the proxy host with the privileges of the proxy process. The endpoints were gated only by a valid proxy API key, with no role check. Any authenticated user — including holders of low-privilege internal-user keys — could therefore run arbitrary commands on the host. This issue has been patched in version 1.83.7.
References
| Link | Resource |
|---|---|
| https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable | Product Release Notes |
| https://github.com/BerriAI/litellm/security/advisories/GHSA-v4p8-mg3p-g94g | Mitigation Patch Vendor Advisory |
Configurations
History
08 May 2026, 20:04
| Type | Values Removed | Values Added |
|---|---|---|
| CPE | cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:* | |
| CVSS |
v2 : v3 : |
v2 : unknown
v3 : 8.8 |
| First Time |
Litellm litellm
Litellm |
|
| References | () https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable - Product, Release Notes | |
| References | () https://github.com/BerriAI/litellm/security/advisories/GHSA-v4p8-mg3p-g94g - Mitigation, Patch, Vendor Advisory |
08 May 2026, 04:16
| Type | Values Removed | Values Added |
|---|---|---|
| New CVE |
Information
Published : 2026-05-08 04:16
Updated : 2026-05-08 20:04
NVD link : CVE-2026-42271
Mitre link : CVE-2026-42271
CVE.ORG link : CVE-2026-42271
JSON object : View
Products Affected
litellm
- litellm