VllmApplication

CVE-2025-30165

HIGH · 8.0 CVSS v3.1 Published 2025-05-06
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
82/100
Remediation priority · High
Zero-click

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
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.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · high confidence

In multi-node V0 engine deployments using tensor parallelism, secondary vLLM hosts connect via ZeroMQ SUB sockets to the primary's XPUB socket. When data is received on the SUB socket, it is deserialized using Python's pickle module, which is unsafe because pickle can execute arbitrary code during deserialization. This creates a remote code execution vector that can be exploited if an attacker compromises the primary host or performs ARP cache poisoning to redirect traffic.

MitigationDeploy V1 engine instead of V0, as V1 is not affected. If V0 must be used, ensure the deployment is on a fully secured network segment isolated from untrusted traffic, as recommended by maintainers.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.

NVD · CPE data
VllmApplication
Affected:>= 0.5.2

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Adjacent
Complexity
Low
Privileges
Low
User interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Identify vLLM version
    Run 'pip show vllm' or check the installed vllm package version
    Affected if version is 0.5.2 or higher and the deployment uses the V0 engine with tensor parallelism
  2. Verify tensor parallelism configuration
    Check the vLLM deployment configuration or startup arguments for tensor parallel settings (e.g., --tensor-parallel-size greater than 1, or corresponding environment/config setting)
    Affected if tensor-parallel-size is set to value greater than 1, indicating a multi-node deployment
  3. Confirm V0 engine is in use
    Inspect the vLLM startup logs or configuration for engine type; check for absence of V1 engine flags or explicit V0 configuration
    Affected if V0 engine is explicitly configured or V1 engine is NOT enabled (V1 is not affected per vendor)
  4. Check for ZeroMQ network exposure
    Review deployment network configuration and inspect vLLM logs for XPUB/SUB socket connections between nodes
    Affected if the multi-node V0 deployment has ZeroMQ communication between nodes that could be intercepted or redirected by an attacker

A user is affected if running vllm version 0.5.2 or higher with V0 engine and tensor parallelism enabled across multiple nodes, where the ZeroMQ communication channel between primary and secondary hosts could be compromised.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

dbcve · scoped
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Deploy V1 engine instead of V0, as V1 is not affected. If V0 must be used, ensure the deployment is on a fully secured network segment isolated from untrusted traffic, as recommended by maintainers.

Recommended fix High confidence
  1. If using the V0 engine with multi-node tensor parallelism deployments, migrate to the V1 engine which is not affected by this vulnerability
  2. If migration to V1 is not feasible, ensure the multi-node vLLM deployment is on a secure, isolated network to prevent ARP cache poisoning and other network-based attacks
  3. Avoid exposing ZeroMQ ports used for multi-node communication to untrusted networks
  4. Consider disabling tensor parallelism across multiple hosts if the deployment pattern is not essential
  5. Implement network segmentation and firewalls to restrict access to the primary vLLM host's XPUB socket
Caveat Migrating to V1 engine may require code changes if V0-specific APIs are used

Generated from the published advisory — verify against the referenced sources before acting.

Fix this in Vllm Scoped from the published advisory
  • Consultation2.0 h
  • Implementation4.0 h
  • Testing2.0 h
  • Review / QA1.0 h
9.0 hours of engineering $1,600
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $2,560.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2025-30165 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2025-30165 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data