9.1

CVE-2025-29783: vllm-project vllm Deserialization of Untrusted Data

CVSS: 9.1v3.1CriticalAnalyzed
AliasesGHSA-x3m8-f7g5-qhm7PYSEC-2025-63
Published 19-03-2025Last modified 22-03-2025

Vulnerability summary

CVE-2025-29783 is a critical (CVSS 9.1) Deserialization of Untrusted Data vulnerability in vllm-project vllm. EPSS estimates a 0.73% chance of exploitation in the next 30 days, higher than 53.6% of scored vulnerabilities.

Overall risk
70/100
0100
High · default modelHow is this calculated?
CVSS score
9.1/10
010
Critical · v3.1 (CVE.org)
EPSS score
0.73%
0%100%
Low · +0.01 pp in 30 days
KEVNot listedIn no KEV catalog
RansomwareNone recordedNo known use recorded
Public exploits0No public exploits recorded

Advisory lineage

Upstream 0 · Downstream 0 · Related 4

Timeline

  1. 19-03-2025
    PublishedVulnerability first disclosed.
  2. 22-03-2025
    Last modifiedVulnerability information updated.

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.

CVSS metrics

3 scores · 3 sources · 1 version

EPSS trend

Probability

0.73%

Chance of exploitation in the next 30 days

Percentile

54%

Versus all other CVEs

30-day change

+0.01 pp

From 0.73% on 20-09-2026

20-09-202620-10-2026
EPSS score
0.73%

Known exploited

Compare KEV catalogs

Not in any of the 3 tracked catalogs.

Public exploits

0 found

No public exploits indexed.

Weaknesses

CWE · root cause

Affected systems

PyPI1 product
  • vllm< 288ca110f68d23909728627d3100e5a8db820aa2 | ≥ 0.6.5, < 0.8.0
Vllm1 product
  • vllm≥ 0.6.5, < 0.8.0
Vllm-project1 product
  • vllm≥ 0.6.5, < 0.8.0

3 vendors · 3 products

References

6 links