CVE-2026-42271: BerriAI LiteLLM Command Injection Vulnerability

High severity, CVSS 8.8. Actively exploited: in CISA KEV since 2026-06-08. EPSS: 92.6% chance of exploitation in the next 30 days.

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.

Affected products

• LiteLLM LiteLLM: from 1.74.2, before 1.83.7 (fixed in 1.83.7)
• Red Hat Openshift Ai: from 2.25, before 2.25.8 (fixed in 2.25.8); from 3.3, before 3.3.4 (fixed in 3.3.4); version 3.4 only

Published 2026-05-08. Last modified 2026-07-15.