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.

The version of the LiteLLM Python package installed on the remote host is 1.74.2 before 1.83.7. It is, therefore, affected by a vulnerability:

  - 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. (CVE-2026-42271)

Note that Nessus has not tested for this issue but has instead relied only on the application's self-reported version number.

According to its self-reported version, the instance of LiteLLM running on the remote web server is prior to 1.83.7. It is, therefore, affected by multiple vulnerabilities :

- An SQL Injection in the Proxy API Key verification flow.

- An Authenticated command execution via MCP stdio test endpoints

Note that the scanner has not tested for these issues but has instead relied only on the application's self-reported version number.

There are packages installed that are affected by a vulnerability referenced in the following CVE:

  - 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. (CVE-2026-42271)

ID	Name	Product	Family	Severity
324115	LiteLLM 1.74.2 < 1.83.7 Command Injection Vulnerability (GHSA-v4p8-mg3p-g94g)	Nessus	Artificial Intelligence	high
115229	LiteLLM < 1.83.7 Multiples Vulnerabilities	Web App Scanning	Artificial Intelligence	critical
440896	SCA: security update for litellm (GHSA-v4p8-mg3p-g94g)	Tenable Cloud Security	SCA Checks	high
440896	SCA: security update for litellm (GHSA-v4p8-mg3p-g94g)	Tenable Self-Hosted Container Security	SCA Checks	high

Detections

Analytics

CVE-2026-42271

high

Tenable Plugins

high

critical

high

high