GitHub Advisoryadvisory · PyPI

GHSA-v4p8-mg3p-g94g LiteLLM: Authenticated command execution via MCP stdio test endpoints

HIGH Published 2026-04-25 Modified 2026-06-09 Official page ↗
Aliases
CVE-2026-42271
Ecosystem
PyPI
Packages
litellm
Severity
High
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Weaknesses
CWE-77, CWE-78
Reviewed
2026-04-25

Affected packages

• PyPI litellm: >= 1.74.2, < 1.83.7 → fixed in 1.83.7

Description

Impact 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. Patches Fixed in `1.83.7`. Both test endpoints now require the `PROXY_ADMIN` role, bringing them into line with the save endpoint. Workarounds If upgrading is not immediately possible, developers should block `POST /mcp-rest/test/connection` and `POST /mcp-rest/test/tools/list` at their reverse proxy or API gateway.

Related

Alias · CVE (1)

  • CVE-2026-42271 LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. vulnerability

Weakness · CWE (2)

  • CWE-77 Improper Neutralization of Special Elements used in a Command weakness
  • CWE-78 Improper Neutralization of Special Elements used in an OS Command weakness

References