Deserialization in Vllm

CVE-2025-29783

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code execution vulnerability impacting any deployments using Mooncake to distribute KV across distributed hosts. This vulnerability is fixed in 0.8.0.

Vulnerability class: Insecure Deserialization

Published · last modified .

CVSS v3 metric

CVSS v3 base score 9.0 (Critical). Vector: CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H.

EPSS exploit prediction

EPSS: 0.007 (53.5th percentile), scored .

Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 54th percentile — 53.5% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.

EPSS trend (30 days)EPSS over the last 30 days for CVE-2025-29783: held from 0.007 to 0.007.

EPSS over last 30 days · oldest: 0.007 · newest: 0.007 · change: +0.000

Affected products

Weakness classification (CWE)

Public proof-of-concept exploits

References

Frequently asked questions

What is CVE-2025-29783?
CVE-2025-29783 is a critical-severity vulnerability in Vllm, classified under Deserialization of Untrusted Data. CVSS score: 9.0/10. Published 2025-03-19.
How severe is CVE-2025-29783?
Critical severity. CVSS v3 base score is 9.0 out of 10.
Is CVE-2025-29783 known to be exploited?
1 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.