📌 이 취약점에 대해 확인된 사실
전부 발행처가 발표한 값입니다. 우리가 계산하거나 판단한 숫자는 하나도 없습니다.
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)
91.4%
📄 원문 그대로
아래 문장은 전부 발행처가 쓴 것입니다. 번역하지 않습니다 — 보안 문서의 오역은 조치를 바꿉니다.
취약점 설명 (NVD)
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 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
악용 확률 변화
우리가 매일 저장한 EPSS 스냅샷입니다. 원본은 전날 값만 주므로, 이 표는 수집을 시작한 이후만 보여줍니다.
| 기준일 | 확률 | 백분위 |
|---|---|---|
| 2026-11-02 | 91.44% | 99.8% |
| 2026-11-01 | 91.44% | 99.8% |
| 2026-10-31 | 91.44% | 99.8% |
| 2026-10-30 | 91.44% | 99.8% |
| 2026-10-29 | 91.44% | 99.8% |
| 2026-10-28 | 91.44% | 99.8% |
| 2026-10-27 | 91.44% | 99.8% |
| 2026-10-26 | 91.44% | 99.8% |
| 2026-10-25 | 91.44% | 99.8% |
| 2026-10-24 | 92.57% | 99.8% |
| 2026-10-23 | 92.57% | 99.8% |
| 2026-10-22 | 92.57% | 99.8% |
| 2026-10-21 | 92.57% | 99.8% |
| 2026-10-20 | 92.57% | 99.8% |
🧩 같은 약점 유형 — CWE-77
같은 분류의 다른 취약점입니다. 같은 실수가 제품을 가리지 않고 반복됩니다.