Skip to content
Threat Brief

← All advisories

CVE-2026-42271

High 8.7KEV · exploitedFix status unknown

LiteLLM: Authenticated command execution via MCP stdio test endpoints

Record last updated

CVSS score

8.7

High on a 0 to 10 scale

EPSS, chance of exploitation in 30 days

91%

Among the highest-scored CVEs. A prediction, not evidence.

CISA remediation deadline

152days overdue

Passed 152 days ago for U.S. federal agencies

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.

Weakness: CWE-77, CWE-78

Patching and mitigation

Patch status
Unknown: no source documents a fix
Mitigation
None documented
Vendor guidance
access.redhat.com (opens in a new tab)

Affected products

VendorProductAffected versionsFixed inPer
BerriAILiteLLMNot documentedNot documentedCISA KEV
BerriAIlitellm>= 1.74.2, < 1.83.7Not documentedCVE Program

Timeline

  1. Disclosure

    CVE record published by GitHub_M

    Source: CVE Program (opens in a new tab)

  2. 08 Jun 2026KEV

    Added to the CISA Known Exploited Vulnerabilities catalog

    Source: CISA KEV (opens in a new tab)

  3. 08 Jun 2026Exploitation

    Exploitation confirmed by CISA KEV

    Source: CISA KEV (opens in a new tab)

Vendor guidance and references