Skip to content
StratQuad

Threats

BerriAI LiteLLM Command Injection Vulnerability

CVE-2026-42271Known exploitedHigh

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.

Description from the US National Vulnerability Database.

Scores and dates

CVSS 4.0
8.7
HIGH
EPSS score
0.91
Probability of exploitation in 30 days
EPSS percentile
99th
Share of scored CVEs at or below this one
Added to KEV
8 Jun
CISA due date
22 Jun
Applies to US federal agencies

CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Daily EPSS score, 3 Nov to 15 Nov, source FIRST

Detail

BerriAI LiteLLM. CISA required action: Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable.

Weakness: CWE-77 (opens in a new tab), CWE-78 (opens in a new tab)

Affected versions

  • litellm litellm: from 1.74.2, before 1.83.7
  • redhat openshift ai: from 2.25, before 2.25.8
  • redhat openshift ai: from 3.3, before 3.3.4
  • redhat openshift ai: 3.4