Skip to main content

Vllm CVE-2025-32444

CRITICAL
Deserialization of Untrusted Data (CWE-502)
2025-04-30 security-advisories@github.com
10.0
CVSS 3.1 · GitHub Advisory
Share

Severity by source

GitHub Advisory PRIMARY
10.0 CRITICAL
AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
Red Hat
10.0 CRITICAL
qualitative

Primary rating from GitHub Advisory.

CVSS VectorGitHub Advisory

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Changed
Confidentiality
High
Integrity
High
Availability
High

Lifecycle Timeline

4
Analysis Generated
Mar 28, 2026 - 18:39 vuln.today
Patch released
Mar 28, 2026 - 18:39 nvd
Patch available
PoC Detected
May 28, 2025 - 19:12 vuln.today
Public exploit code
CVE Published
Apr 30, 2025 - 01:15 nvd
CRITICAL 10.0

DescriptionGitHub Advisory

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.

AnalysisAI

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Rated critical severity (CVSS 10.0), this vulnerability is remotely exploitable, no authentication required, low attack complexity. Public exploit code available.

Technical ContextAI

This vulnerability is classified as Deserialization of Untrusted Data (CWE-502), which allows attackers to execute arbitrary code through malicious serialized objects. 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. Affected products include: Vllm. Version information: prior to 0.8.5.

RemediationAI

A vendor patch is available. Apply the latest security update as soon as possible. Avoid deserializing untrusted data. Use safe serialization formats (JSON). Implement integrity checks and type allowlists.

Vendor StatusVendor

Share

CVE-2025-32444 vulnerability details – vuln.today

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy