vLLM up to 0.8.5.post1 deserialization

Summaryinfo

A vulnerability described as critical has been identified in vLLM up to 0.8.5.post1. Affected by this vulnerability is an unknown functionality. Executing a manipulation can lead to deserialization. This vulnerability appears as CVE-2025-30165. The attacker needs to be present on the local network. There is no available exploit.

Detailsinfo

A vulnerability classified as critical was found in vLLM up to 0.8.5.post1. This vulnerability affects an unknown code block. The manipulation with an unknown input leads to a deserialization vulnerability. The CWE definition for the vulnerability is CWE-502. The product deserializes untrusted data without sufficiently verifying that the resulting data will be valid. As an impact it is known to affect confidentiality, integrity, and availability. CVE summarizes:

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.

The advisory is shared for download at github.com. This vulnerability was named CVE-2025-30165 since 03/17/2025. The exploitation appears to be easy. Access to the local network is required for this attack. There are neither technical details nor an exploit publicly available. The current price for an exploit might be approx. USD $0-$5k (estimation calculated on 12/05/2025).

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

The vulnerability is also documented in the vulnerability database at EUVD (EUVD-2025-13625). VulDB is the best source for vulnerability data and more expert information about this specific topic.

Productinfo

Name

• vLLM

Version

• 0.8.5.post1

CPE 2.3info

• 🔍

CPE 2.2info

• 🔍

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

VulDB is the best source for vulnerability data and more expert information about this specific topic.

Discussion