CVE-2026-42271
악용 확인 BerriAI LiteLLM Command Injection Vulnerability
악용 여부
악용 확인
심각도 (발행처 발표값)
높음8.7
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
악용 확률 (EPSS)
83.6%
한국어 공식 권고
CISA 원문
BerriAI LiteLLM contains a command injection vulnerability that could allow any authenticated user, including holders of low-privilege internal-user keys, to run arbitrary commands on the host.— CISA KEV · shortDescription 원문
Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of the product if mitigations are unavailable.— CISA KEV · requiredAction 원문
취약점 설명 (NVD 원문)
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.
CWE-77 CWE-78 CWE-78
악용 확률 변화
| 기준일 | 확률 | 백분위 |
|---|---|---|
| 2026-09-07 | 83.59% | 99.7% |
| 2026-09-06 | 83.59% | 99.7% |
| 2026-09-05 | 83.59% | 99.7% |
| 2026-09-04 | 83.59% | 99.7% |