CVE-2025-30165

Remote Code Execution Vulnerability in vLLM Multi-Node Cluster Configuration

Published May 6, 2025 CVSS 3.1 · 8 High EPSS < 1% KEV · Not listed

Description

vLLM is an inference and serving engine for large language models. In a multi-node vLLM deployment using the V0 engine, vLLM uses ZeroMQ for some multi-node communication purposes. The secondary vLLM hosts open a `SUB` ZeroMQ socket and connect to an `XPUB` socket on the primary vLLM host. When data is received on this `SUB` socket, it is deserialized with `pickle`. This is unsafe, as it can be abused to execute code on a remote machine. Since the vulnerability exists in a client that connects to the primary vLLM host, this vulnerability serves as an escalation point. If the primary vLLM host is compromised, this vulnerability could be used to compromise the rest of the hosts in the vLLM deployment. Attackers could also use other means to exploit the vulnerability without requiring access to the primary vLLM host. One example would be the use of ARP cache poisoning to redirect traffic to a malicious endpoint used to deliver a payload with arbitrary code to execute on the target machine. Note that this issue only affects the V0 engine, which has been off by default since v0.8.0. Further, the issue only applies to a deployment using tensor parallelism across multiple hosts, which we do not expect to be a common deployment pattern. Since V0 is has been off by default since v0.8.0 and the fix is fairly invasive, the maintainers of vLLM have decided not to fix this issue. Instead, the maintainers recommend that users ensure their environment is on a secure network in case this pattern is in use. The V1 engine is not affected by this issue.

Affected Products

Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).

Vendor Product Default status Versions

vllm-project

vllm

affected

Version	Status	Constraints
`>= 0.5.2, <= 0.8.5.post1`	affected	—

Configuration 1 [-]

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

No data.

No data available yet.

Remediation

No solution or workaround provided in the CVE record

Tracking

Advisories

Source	ID	Title
EUVD	EUVD-2025-13625	vLLM is an inference and serving engine for large language models. In a multi-node vLLM deployment using the V0 engine, vLLM uses ZeroMQ for some multi-node communication purposes. The secondary vLLM hosts open a `SUB` ZeroMQ socket and connect to an `XPUB` socket on the primary vLLM host. When data is received on this `SUB` socket, it is deserialized with `pickle`. This is unsafe, as it can be abused to execute code on a remote machine. Since the vulnerability exists in a client that connects to the primary vLLM host, this vulnerability serves as an escalation point. If the primary vLLM host is compromised, this vulnerability could be used to compromise the rest of the hosts in the vLLM deployment. Attackers could also use other means to exploit the vulnerability without requiring access to the primary vLLM host. One example would be the use of ARP cache poisoning to redirect traffic to a malicious endpoint used to deliver a payload with arbitrary code to execute on the target machine. Note that this issue only affects the V0 engine, which has been off by default since v0.8.0. Further, the issue only applies to a deployment using tensor parallelism across multiple hosts, which we do not expect to be a common deployment pattern. Since V0 is has been off by default since v0.8.0 and the fix is fairly invasive, the maintainers of vLLM have decided not to fix this issue. Instead, the maintainers recommend that users ensure their environment is on a secure network in case this pattern is in use. The V1 engine is not affected by this issue.
Github GHSA	GHSA-9pcc-gvx5-r5wm	Remote Code Execution Vulnerability in vLLM Multi-Node Cluster Configuration

Metrics

No CVSS v4.0

Attack Vector Adjacent Network

Attack Complexity Low

Privileges Required Low

Scope Unchanged

Confidentiality Impact High

Integrity Impact High

Availability Impact High

User Interaction None

No CVSS v3.0

No CVSS v2

This CVE is not in the KEV list.

Exploit prediction score: < 1% (0.562% probability within 30 days)

Exploitation none

Automatable no

Technical Impact total

References

Link	Providers
https://github.com/vllm-project/vllm/blob/c21b99b91241409c2fdf9f3f8c542e8748b317be/vllm/distributed/device_communicators/shm_broadcast.py#L295-L301
https://github.com/vllm-project/vllm/blob/c21b99b91241409c2fdf9f3f8c542e8748b317be/vllm/distributed/device_communicators/shm_broadcast.py#L468-L470
https://github.com/vllm-project/vllm/security/advisories/GHSA-9pcc-gvx5-r5wm
https://nvd.nist.gov/vuln/detail/CVE-2025-30165
https://www.cve.org/CVERecord?id=CVE-2025-30165

History

Jul 31, 2025 6:15 PM First appearance in the feed. Affected versions updated. Affected vendors updated View changes

Type	Values Removed	Values Added
First Time appeared		Vllm Vllm vllm
CPEs		cpe:2.3:a:vllm:vllm::::::::
Vendors & Products		Vllm Vllm vllm

Jul 13, 2025 1:45 PM Scoring metrics updated View changes

Type	Values Removed	Values Added
Metrics	epss `{'score': 0.00276}`	epss `{'score': 0.00277}`

May 20, 2025 2:30 AM Added references. Scoring metrics updated View changes

Type	Values Removed	Values Added
References		https://nvd.nist.gov/vuln/detail/CVE-2025-30165 https://www.cve.org/CVERecord?id=CVE-2025-30165
Metrics	threat_severity `None`	threat_severity `Important`

May 6, 2025 6:15 PM Scoring metrics updated View changes

Type	Values Removed	Values Added
Metrics		ssvc `{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'total'}, 'version': '2.0.3'}`

May 6, 2025 5:00 PM Description updated. Title updated. Weaknesses updated. Added references. Scoring metrics updated View changes

Type	Values Removed	Values Added
Description		vLLM is an inference and serving engine for large language models. In a multi-node vLLM deployment using the V0 engine, vLLM uses ZeroMQ for some multi-node communication purposes. The secondary vLLM hosts open a `SUB` ZeroMQ socket and connect to an `XPUB` socket on the primary vLLM host. When data is received on this `SUB` socket, it is deserialized with `pickle`. This is unsafe, as it can be abused to execute code on a remote machine. Since the vulnerability exists in a client that connects to the primary vLLM host, this vulnerability serves as an escalation point. If the primary vLLM host is compromised, this vulnerability could be used to compromise the rest of the hosts in the vLLM deployment. Attackers could also use other means to exploit the vulnerability without requiring access to the primary vLLM host. One example would be the use of ARP cache poisoning to redirect traffic to a malicious endpoint used to deliver a payload with arbitrary code to execute on the target machine. Note that this issue only affects the V0 engine, which has been off by default since v0.8.0. Further, the issue only applies to a deployment using tensor parallelism across multiple hosts, which we do not expect to be a common deployment pattern. Since V0 is has been off by default since v0.8.0 and the fix is fairly invasive, the maintainers of vLLM have decided not to fix this issue. Instead, the maintainers recommend that users ensure their environment is on a secure network in case this pattern is in use. The V1 engine is not affected by this issue.
Title		Remote Code Execution Vulnerability in vLLM Multi-Node Cluster Configuration
Weaknesses		CWE-502
References		https://github.com/vllm-project/vllm/blob/c21b99b91241409c2fdf9f3f8c542e8748b317be/vllm/distributed/device_communicators/shm_broadcast.py#L295-L301 https://github.com/vllm-project/vllm/blob/c21b99b91241409c2fdf9f3f8c542e8748b317be/vllm/distributed/device_communicators/shm_broadcast.py#L468-L470 https://github.com/vllm-project/vllm/security/advisories/GHSA-9pcc-gvx5-r5wm
Metrics		cvssV3_1 `{'score': 8, 'vector': 'CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H'}`