cve.bz

CVE-2025-30165 (ShadowMQ) vllm vllm: Deserialization of Untrusted Data

8.0 highEPSS 0.6%Fix available

Known as ShadowMQ

High (8.0) in vllm vllm. EPSS 0.6% estimated probability of exploitation activity in the next 30 days. Fixed in vllm 0.10.0.

On this page
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.

Severity

CVSS 3.1

8.0 high
CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
EPSS
0.6% (unchanged from 0.6% a week ago; 0.6% 30 days ago) estimated probability of exploitation activity in the next 30 days; 48th percentile. Scored 2026-11-21. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: none · Automatable: no · Technical impact: total, assessed 2025-05-06. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWE
CWE-502 Deserialization of Untrusted Data
OWASP Top 10
A08:2025 Software or Data Integrity Failures
Published
Modified
NVD analysis
Analyzed
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2025-30165 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2025-30165?via=ask-ai-copy and https://cve.bz/cve/CVE-2025-30165?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2025-30165 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the NVD's CPE matches.

ProductAffected
vllm:vllm0.5.2 and later

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-9pcc-gvx5-r5wmPyPIvllm>=0.5.2 <0.10.00.10.0
PYSEC-2026-2017PyPIvllm>=0.5.2 <0.10.00.10.0

Red Hat

Red Hat rates this Important.

Red Hat's statement

No Red Hat products are affected by these vulnerabilities.

These vulnerabilities are marked as high severity due to their direct impact on security and data confidentiality in multi-node vLLM deployments.The use of unsafe deserialization with pickle over a ZeroMQ SUB socket allows an attacker to execute arbitrary code remotely. If the primary vLLM node is compromised, this flaw can be used to escalate privileges and execute malicious code on secondary hosts, impacting the entire deployment. This lack of input validation and the insecure use of serialization mechanisms significantly increase the exploitability of this issue, leading to its classification as a high severity vulnerability.

In RHOAI, vLLM is not included by default in RHOAI deployment as an operator or controller . Hence, RHOAI is not-affected.

Red Hat's mitigation

Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base or stability.

ProductPackageStateAdvisory
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/bootc-amd-rhel9Not affected
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/bootc-aws-nvidia-rhel9Not affected
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/bootc-azure-amd-rhel9Not affected
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/bootc-azure-nvidia-rhel9Not affected
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/bootc-gcp-nvidia-rhel9Not affected
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/bootc-ibm-nvidia-rhel9Not affected
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/bootc-intel-rhel9Not affected
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/bootc-nvidia-rhel9Not affected
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/instructlab-amd-rhel9Not affected
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/instructlab-intel-rhel9Not affected
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/instructlab-nvidia-rhel9Not affected
Red Hat Enterprise Linux AI (RHEL AI)rhelai1/ui-rhel9Not affected

Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2025-30165.

Attack patterns (CAPEC)

  • CAPEC-586 Object Injection Likelihood: Medium · Severity: High

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.

References

Check your stackJSON