CVE-2026-42271
Description
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.
How to fix
Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable.
CISA due date: Jun 22, 2026- litellm litellm1.83.7 or later
- redhat openshift_ai2.25.8, 3.3.4 or later
- litellm1.83.7 or later
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| litellm litellm | 1.74.2 ≤ v < 1.83.7 | 1.83.7 |
| redhat openshift_ai | 2.25 ≤ v < 2.25.8, 3.3 ≤ v < 3.3.4, 3.4 | 2.25.8, 3.3.4 |
| litellmPyPI | 1.74.2 ≤ v < 1.83.7 | 1.83.7 |
Check your version
Choose the product and enter the version you run to see whether it falls in the affected range.
Attack Surface Management
See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.