← Back to CVE List
Vulnerability Intelligence Report
LiteLLM: Authenticated command execution via MCP stdio test endpoints

CVE-2026-42271

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.

CISA KEV Nuclei Template SSVC: Active Exploitation Injection
CVSS Base Score
8.7
HIGH
EPSS Probability:80.19%
Executive Threat Verdict
Evaluating...
Evaluating Threat Landscape...
Assessing known weaponization, exploitation telemetry, and federal advisories.
Attack Surface
—
Authentication
—
Weaponization
—
SSVC Action
—

Weaknesses (CWE)

CWE-77 ↗CWE-77: Improper Neutralization of Special Elements used in a Command ('Command Injection')
CWE-78 ↗CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')

Affected Products & Versions

Vendor Product Affected Versions
BerriAI litellm >= 1.74.2, < 1.83.7 (affected)

References & Technical Advisories

No reference links found.

Threat Intelligence Signals

CISA KEV
ACTIVE IN CATALOG
Nuclei Template
SCANNER AVAILABLE
EPSS Score
80.188%
Vulnerability Class
Injection

Identity & Timeline

StatusPUBLISHED
Assigning AuthorityGitHub, Inc. · Vendor · USA
Reserved2026-04-26T11:53:27
Published2026-05-08T03:35:16
Last Updated2026-07-15T00:57:49

LINK COPIED TO CLIPBOARD