← Back to Vulnerability Reports CVE Intelligence

CVE-2026-42271

BerriAI LiteLLMHIGH · CVSS 8.8 In the wild In CISA KEV

What is 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.

CVSS8.8 NVD 3.1
SeverityHIGH
Exploitation In the wild In CISA KEV
EPSS61% · P98
Triage statusActive Exploit
ActionPatch immediately
CVSS vectorCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CWECWE-77
NVD published2026-05-08
NVD last modified2026-06-09

CISA Known Exploited Vulnerability

BerriAI LiteLLM Command Injection Vulnerability

Added to KEV2026-06-08
Federal patch deadline2026-06-22
Known ransomware useUnknown

Affected product

BerriAI LiteLLM

Remediation Steps

  1. Apply security patches from BerriAI for LiteLLM
  2. Review and restrict input validation on LiteLLM command interfaces
  3. Audit recent LiteLLM command execution logs for exploitation attempts
  4. Update to the latest stable version of LiteLLM

Coverage on defend.network

🤖 This CVE page is generated by defend.network from NVD, CISA KEV, EPSS, and our verified daily briefings. Severity and exploitation data come from official sources; always verify remediation steps against the official vendor advisory before acting in production.

Get Critical CVE Alerts

Subscribe free and hear about actively exploited CVEs like this one first.