CVE-2025-30165
CVE-2025-30165 is a high-severity vulnerability in Vllm with a CVSS 3.x base score of 8.0. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-502.
Key facts
- Severity: High (CVSS 3.x base score 8.0)
- EPSS exploit prediction: 1% (39th percentile)
- Actively exploited: Not listed in CISA KEV
- EU (EUVD) id: EUVD-2025-13625
- Weakness: CWE-502
- Affected product: Vllm
- Published:
- Last modified:
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.
Frequently asked questions
- What is CVE-2025-30165?
- 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.
- How severe is CVE-2025-30165?
- CVE-2025-30165 has a CVSS 3.x base score of 8.0, rated high severity. It is exploitable over an adjacent network with low attack complexity, requires low privileges and no user interaction. Impact on confidentiality is high, integrity high, and availability high.
- Is CVE-2025-30165 being actively exploited?
- It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 1% (39th percentile), an estimate of the probability of exploitation in the next 30 days.
- What products are affected by CVE-2025-30165?
- CVE-2025-30165 affects Vllm. See the affected-products list for the exact vulnerable versions.
- How do I fix CVE-2025-30165?
- Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its high severity, prioritise patching exposed systems.
- Does CVE-2025-30165 have an EU (EUVD) identifier?
- Yes. CVE-2025-30165 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2025-13625.
- When was CVE-2025-30165 published?
- CVE-2025-30165 was published on 2025-05-06 and last updated on 2026-06-17.
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
Affected products (1)
- cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
More vulnerabilities in Vllm
- CVE-2025-32444 — Critical (CVSS 10.0): vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and…
- CVE-2026-22778 — Critical (CVSS 9.8): vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid…
- CVE-2025-47277 — Critical (CVSS 9.8): vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4…
- CVE-2024-11041 — Critical (CVSS 9.8): vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. The function uses…
- CVE-2026-48746 — Critical (CVSS 9.1): vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerability in…
- CVE-2025-29783 — Critical (CVSS 9.0): vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use…
Other CWE-502 (Deserialization of Untrusted Data) vulnerabilities
- CVE-2026-41104 — Critical (CVSS 10.0): Deserialization of untrusted data in Microsoft Planetary Computer Pro allows an unauthorized attacker to disclose…
- CVE-2026-43633 — Critical (CVSS 10.0): HestiaCP versions 1.9.0 through 1.9.4 contain a deserialization vulnerability in the web terminal component caused by a…
- CVE-2026-33819 — Critical (CVSS 10.0): Deserialization of untrusted data in Microsoft Bing allows an unauthorized attacker to execute code over a network.
- CVE-2026-20131 — Critical (CVSS 10.0): A vulnerability in the web-based management interface of Cisco Secure Firewall Management Center (FMC) Software could…
- CVE-2026-25632 — Critical (CVSS 10.0): EPyT-Flow is a Python package designed for the easy generation of hydraulic and water quality scenario data of water…
- CVE-2025-14931 — Critical (CVSS 10.0): Hugging Face smolagents Remote Python Executor Deserialization of Untrusted Data Remote Code Execution Vulnerability.…
Browse all CWE-502 (Deserialization of Untrusted Data) vulnerabilities →