vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and prior to 0.8.5, having vLLM integration with mooncake, are vulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. The vulnerable sockets were set to listen on all network interfaces, increasing the likelihood that an attacker is able to reach the vulnerable ZeroMQ sockets to carry out an attack. vLLM instances that do not make use of the mooncake integration are not vulnerable. This issue has been patched in version 0.8.5.
beschreibt (1)
Zugehörige CVEs.
| ID | Schweregrad | ausnutzbar | ||
|---|---|---|---|---|
| CVE-2025-32444US | critical9.8 | — | ||
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and prior to 0.8.5, having vLLM integration with mooncake, are vu… | ||||
Referenzen
Externe Belege — Patches, Meldungen, Analysen.
- https://github.com/advisories/GHSA-hj4w-hm2g-p6w5ADVISORY
- https://github.com/vllm-project/vllm/blob/32b14baf8a1f7195ca09484de3008063569b43c5/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py#L179WEB
- https://github.com/vllm-project/vllm/commit/a5450f11c95847cf51a17207af9a3ca5ab569b2cFIX
- https://github.com/vllm-project/vllm/security/advisories/GHSA-hj4w-hm2g-p6w5EVIDENCE
- https://github.com/vllm-project/vllm/security/advisories/GHSA-x3m8-f7g5-qhm7ADVISORY
Advisories wie diese benennen die exponierten Produkte, die Angreifer auf Ihrer Angriffsfläche ins Visier nehmen. Sehen Sie mit einem kostenlosen Passiv-Scan, was exponiert ist.
Kostenloser Scan