vllm up to 0.8.4 ZeroMQ allocation of resources

Summaryinfo

A vulnerability classified as critical has been found in vllm up to 0.8.4. This issue affects some unknown processing of the component ZeroMQ. Performing a manipulation results in allocation of resources. This vulnerability is known as CVE-2025-30202. Remote exploitation of the attack is possible. No exploit is available. It is recommended to upgrade the affected component.

Detailsinfo

A vulnerability classified as critical has been found in vllm up to 0.8.4. This affects some unknown processing of the component ZeroMQ. The manipulation with an unknown input leads to a allocation of resources vulnerability. CWE is classifying the issue as CWE-770. The product allocates a reusable resource or group of resources on behalf of an actor without imposing any restrictions on the size or number of resources that can be allocated, in violation of the intended security policy for that actor. This is going to have an impact on availability. The summary by CVE is:

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.5.2 and prior to 0.8.5 are vulnerable to denial of service and data exposure via ZeroMQ on multi-node vLLM deployment. In a multi-node vLLM deployment, vLLM uses ZeroMQ for some multi-node communication purposes. The primary vLLM host opens an XPUB ZeroMQ socket and binds it to ALL interfaces. While the socket is always opened for a multi-node deployment, it is only used when doing tensor parallelism across multiple hosts. Any client with network access to this host can connect to this XPUB socket unless its port is blocked by a firewall. Once connected, these arbitrary clients will receive all of the same data broadcasted to all of the secondary vLLM hosts. This data is internal vLLM state information that is not useful to an attacker. By potentially connecting to this socket many times and not reading data published to them, an attacker can also cause a denial of service by slowing down or potentially blocking the publisher. This issue has been patched in version 0.8.5.

The advisory is shared at github.com. This vulnerability is uniquely identified as CVE-2025-30202 since 03/18/2025. The exploitability is told to be easy. It is possible to initiate the attack remotely. No form of authentication is needed for exploitation. Neither technical details nor an exploit are publicly available. MITRE ATT&CK project uses the attack technique T1499 for this issue.

Upgrading to version 0.8.5 eliminates this vulnerability. Applying the patch a0304dc504c85f421d38ef47c64f83046a13641c is able to eliminate this problem. The bugfix is ready for download at github.com. The best possible mitigation is suggested to be upgrading to the latest version.

Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Productinfo

Name

• vllm

Version

• 0.8.0
• 0.8.1
• 0.8.2
• 0.8.3
• 0.8.4

License

• open-source

CPE 2.3info

• 🔍
• 🔍
• 🔍

CPE 2.2info

• 🔍
• 🔍
• 🔍

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Discussion