CVE-2025-66455
LMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py
- Published
- Updated
- Reserved
- Assigned by
- GitHub_M
Description
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.
Scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| GitHub_MCNA (assigner) | 3.1 | Critical9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| NVDNVD · Awaiting Analysis | 3.1 | Critical9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
- EPSS (exploitation in 30 days)
- 1.3% · top 30% of all CVEs (6 Nov 2026)
- CISA SSVC
- Exploitation: none · Automatable: yes · Technical impact: total
The list uses the assigner's score when there is one, then CISA's, then NVD's: Critical 9.8.
Weakness
Affected products
Affected packages
From reviewed advisories of the GitHub Advisory Database.
- PyPIlmdeployGHSA-2vh9-42vm-xmv2 (opens in a new tab)
References (3)
- https://github.com/InternLM/lmdeploy/security/advisories/GHSA-2vh9-42vm-xmv2 (opens in a new tab)x_refsource_CONFIRM
- https://github.com/InternLM/lmdeploy/commit/f05b4ad8bf2e2d84101a1d63b3c44fadd99223b2 (opens in a new tab)x_refsource_MISC
- https://github.com/InternLM/lmdeploy/releases/tag/v0.16.0 (opens in a new tab)x_refsource_MISC
Sources
The same CVE in the primary databases and aggregators, to check against.
- CVE.org record (opens in a new tab)
- CVE List JSON (GitHub) (opens in a new tab)
- NVD (opens in a new tab)
- FIRST EPSS (opens in a new tab)
- OSV.dev (opens in a new tab)
- GitHub Advisory GHSA-2vh9-42vm-xmv2 (opens in a new tab)
- CIRCL Vulnerability-Lookup (opens in a new tab)
Badge for a README or a ticket
[](https://trackcve.app/cve/CVE-2025-66455)Record last updated .