CVE-2025-29783CRITICAL 9.0EPSS p51.4%

CVE-2025-29783CVE-2025-29783

Description

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.

Scoring

CVSS 3.19.0 (CRITICAL)
VectorCVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
EPSS0.79% probability of exploitation · percentile 51.4% · 2026-06-18T12:00:27Z
Published2025-03-19
Last modified2025-07-01

Underlying weaknesses· 1

CWE-502

References

  1. https://github.com/vllm-project/vllm/commit/288ca110f68d23909728627d3100e5a8db820aa2
  2. https://github.com/vllm-project/vllm/pull/14228
  3. https://github.com/vllm-project/vllm/security/advisories/GHSA-x3m8-f7g5-qhm7

1

TypeTargetConfidenceTier
WeaknessDeserialization of Untrusted Datacwe-5020%live

Related by meaning· 6

Nearest entities by semantic similarity across the cs-graph corpus.

CVE
CVE-2025-32444
CVE
CVE-2026-27893
CVE
CVE-2025-30165
CVE
CVE-2026-22807
CVE
CVE-2025-62164
CVE
CVE-2025-24357
Sourced from NVD + FIRST.org EPSS. Curated for EU compliance use cases by Adam Lundqvist, Founder at SQUR.