Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
vLLM versions 0.6.5 up to but not including 0.8.5 are vulnerable to remote code execution when the Mooncake integration is used, because it deserializes data with pickle over unsecured ZeroMQ sockets that listen on all network interfaces. An attacker with network access to those sockets could execute code on the host. Upgrade to vLLM 0.8.5 or later. Deployments that do not use the Mooncake integration are not affected.
Not analysed yet
We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.
Severity and exploitation
| Score | Rating | CVSS | Vector | Source |
|---|---|---|---|---|
| 10.0 | Critical | 3.1 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H | CNA (GitHub_M) |
- CISA KEV Not listed.
- EPSS 0.018, the 79th percentile, on 18 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:40 UTC First seen by agentprime
- 31 Oct 2026, 14:40 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-hj4w-hm2g-p6w5
- OSV: GHSA-hj4w-hm2g-p6w5
- github.com/vllm-project/vllm/security/advisories/GHSA-hj4w-hm2g-p6w5
- github.com/vllm-project/vllm/security/advisories/GHSA-x3m8-f7g5-qhm7
- nvd.nist.gov/vuln/detail/CVE-2025-32444
- github.com/vllm-project/vllm/commit/a5450f11c95847cf51a17207af9a3ca5ab569b2c
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-42.yaml
- github.com/vllm-project/vllm
- github.com/vllm-project/vllm/blob/32b14baf8a1f7195ca09484de3008063569b43c5/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py#L179