📌 이 취약점에 대해 확인된 사실
전부 발행처가 발표한 값입니다. 우리가 계산하거나 판단한 숫자는 하나도 없습니다.
악용 여부
심각도 (발행처 발표값)
심각9.8
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
악용 확률 (EPSS)
0.7%
📄 원문 그대로
아래 문장은 전부 발행처가 쓴 것입니다. 번역하지 않습니다 — 보안 문서의 오역은 조치를 바꿉니다.
취약점 설명 (NVD)
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.2 and prior to version 0.16.0, LMDeploy's PyTorch DistServe/PD-disaggregation control plane used `recv_pyobj()` to deserialize messages received through a ZeroMQ PULL socket. PyZMQ implements `recv_pyobj()` using Python pickle deserialization, which can execute arbitrary code while reconstructing an object. The peer address used by the receiver was supplied through the `POST /distserve/p2p_connect` HTTP endpoint. An attacker who could reach an affected DistServe API server could cause the server to connect to an attacker-controlled ZeroMQ endpoint and deserialize a crafted pickle payload. API-key authentication is not enabled unless the operator explicitly configures it. As a result, affected DistServe deployments without API keys allowed unauthenticated remote code execution with the privileges of the LMDeploy serving process. This issue affects the PyTorch backend when PD-disaggregation/DistServe is enabled. Ordinary deployments that do not use the affected disaggregated-serving path do not expose this data flow. The fix was released in LMDeploy 0.16.0. Users who cannot upgrade immediately should prevent untrusted clients from reaching `/distserve/*` endpoints, restrict the DistServe HTTP and ZeroMQ control planes to trusted cluster networks, configure API-key authentication, and block arbitrary outbound ZeroMQ connections from serving nodes. These measures reduce exposure but do not make pickle deserialization safe.
참고
악용 확률 변화
우리가 매일 저장한 EPSS 스냅샷입니다. 원본은 전날 값만 주므로, 이 표는 수집을 시작한 이후만 보여줍니다.
| 기준일 | 확률 | 백분위 |
|---|---|---|
| 2026-09-25 | 0.69% | 50.9% |
| 2026-09-24 | 0.69% | 50.8% |
| 2026-09-23 | 0.70% | 51.8% |
| 2026-09-22 | 0.70% | 51.8% |
| 2026-09-21 | 0.70% | 51.4% |
| 2026-09-20 | 0.70% | 51.8% |
| 2026-09-19 | 0.70% | 51.8% |
🧩 같은 약점 유형 — CWE-502
같은 분류의 다른 취약점입니다. 같은 실수가 제품을 가리지 않고 반복됩니다.