Raw vector
CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:HSummary
CVE-2025-30165 is a high-severity Deserialization of Untrusted Data (CWE-502) vulnerability in Vllm Vllm. Its CVSS base score is 8.0 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 42th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as NLP and Transformers; in the Supply Chain and Deployment risk domain.
The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
vLLM is an inference and serving engine for large language models. CVE-2025-30165 is a deserialization vulnerability (CWE-502) that affects only the V0 engine in multi-node deployments that use tensor parallelism across hosts. In this configuration the secondary hosts open a ZeroMQ SUB socket that receives data from an XPUB socket on the primary host and immediately deserializes it with pickle, allowing arbitrary code execution on the receiving host.
An attacker who can reach the SUB socket—either by first compromising the primary vLLM host or by other network-level means such as ARP cache poisoning—can supply a malicious pickle payload that executes code on any secondary host. The vulnerability therefore functions as a lateral-movement vector once an initial foothold exists inside a multi-host V0 deployment.
The vLLM security advisory states that the issue will not be patched because V0 has been disabled by default since version 0.8.0 and the affected multi-host pattern is uncommon. Maintainers instead recommend that organizations using this deployment model keep the cluster on a trusted network; the V1 engine is unaffected.
The associated EPSS score rose from a low baseline to a recorded peak of 0.0131, indicating increased exploitation interest after disclosure.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-13625
Vulnerability Data
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…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- NLP and Transformers
- Risk Domain
- Supply Chain and Deployment
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: vllm
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Mitigating Controls (NIST 800-53 r5) AI
Developer testing and evaluation can uncover deserialization flaws before deployment.
Input validation directly stops deserialization of untrusted data by ensuring inputs are valid before processing.
Engineering principles such as safe deserialization and input sanitization structurally prevent the weakness from being introduced.
Integrity verification tools can detect malformed or tampered serialized data after the fact.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
PR.PS-02 addresses only post-deployment updates/patching and cannot prevent introduction of unsafe deserialization code, yet it can remediate some instances when the flaw exists in outdated libraries or components.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Security testing includes validation of deserialization routines and the use of untrusted data, reducing the likelihood that unsafe object reconstruction will be deployed.
Requiring vetted libraries, regular updates and SAST before release reduces the likelihood that deserialization logic will accept and act on attacker-controlled serialized objects.
Regular scanning of third-party libraries and timely patching reduce the likelihood that unsafe deserialization vulnerabilities remain active.
Mandatory malware scanning of data received over networks or storage media intercepts malicious serialized payloads before they are deserialized by the target application.