Логотип exploitDog
bind:CVE-2025-30202
Консоль
Логотип exploitDog

exploitDog

bind:CVE-2025-30202

Количество 4

Количество 4

redhat логотип

CVE-2025-30202

5 месяцев назад

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 ...

CVSS3: 7.5
EPSS: Низкий
nvd логотип

CVE-2025-30202

5 месяцев назад

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

CVSS3: 7.5
EPSS: Низкий
debian логотип

CVE-2025-30202

5 месяцев назад

vLLM is a high-throughput and memory-efficient inference and serving e ...

CVSS3: 7.5
EPSS: Низкий
github логотип

GHSA-9f8f-2vmf-885j

5 месяцев назад

Data exposure via ZeroMQ on multi-node vLLM deployment

CVSS3: 7.5
EPSS: Низкий

Уязвимостей на страницу

Уязвимость
CVSS
EPSS
Опубликовано
redhat логотип
CVE-2025-30202

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 ...

CVSS3: 7.5
0%
Низкий
5 месяцев назад
nvd логотип
CVE-2025-30202

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

CVSS3: 7.5
0%
Низкий
5 месяцев назад
debian логотип
CVE-2025-30202

vLLM is a high-throughput and memory-efficient inference and serving e ...

CVSS3: 7.5
0%
Низкий
5 месяцев назад
github логотип
GHSA-9f8f-2vmf-885j

Data exposure via ZeroMQ on multi-node vLLM deployment

CVSS3: 7.5
0%
Низкий
5 месяцев назад

Уязвимостей на страницу