What is the CVSS score of CVE-2025-62164?

CVE-2025-62164 has a CVSS 3.1 base score of 8.8 (High). CVSS vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H. EPSS exploitation probability: 0.1%.

Which versions of AI / ML are affected by CVE-2025-62164?

Organizations using vLLM face significant risk from CVE-2025-62164, a input validation vulnerability rated CVSS 8.8.. A patch is available.

How to fix or mitigate CVE-2025-62164?

Within 30 days: Identify all affected systems and apply vendor patches as part of regular patch cycle. Vendor patch is available.

AI / ML CVE-2025-62164

HIGH

Improper Input Validation (CWE-20)

2025-11-21 security-advisories@github.com

RCE Buffer Overflow Red Hat AI / ML Pytorch Vllm

8.8

CVSS 3.1

CVSS VectorNVD

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Attack Vector

Network

Attack Complexity

Low

Privileges Required

Low

User Interaction

None

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High

Lifecycle Timeline

Analysis Generated

Mar 28, 2026 - 19:23 vuln.today

Patch released

Mar 28, 2026 - 19:23 nvd

Patch available

CVE Published

Nov 21, 2025 - 02:15 nvd

HIGH 8.8

Blast Radius

ecosystem impact

† from your stack dependencies † transitive graph · vuln.today resolves 4-path depth

10 pypi packages depend on vllm (10 direct, 0 indirect)

Ecosystem-wide dependent count for version 0.10.2.

DescriptionNVD

vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash (denial-of-service) and potentially remote code execution (RCE), exists in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using torch.load() without sufficient validation. Due to a change introduced in PyTorch 2.8.0, sparse tensor integrity checks are disabled by default. As a result, maliciously crafted tensors can bypass internal bounds checks and trigger an out-of-bounds memory write during the call to to_dense(). This memory corruption can crash vLLM and potentially lead to code execution on the server hosting vLLM. This issue has been patched in version 0.11.1.

AnalysisAI

vLLM is an inference and serving engine for large language models (LLMs). Rated high severity (CVSS 8.8), this vulnerability is remotely exploitable, low attack complexity.

Technical ContextAI

This vulnerability is classified under CWE-20. vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash (denial-of-service) and potentially remote code execution (RCE), exists in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using torch.load() without sufficient validation. Due to a change introduced in PyTorch 2.8.0, sparse tensor integrity checks are disabled by default. As a result, maliciously crafted tensors can bypass internal bounds checks and trigger an out-of-bounds memory write during the call to to_dense(). This memory corruption can crash vLLM and potentially lead to code execution on the server hosting vLLM. This issue has been patched in version 0.11.1. Affected products include: Vllm. Version information: before 0.11.1.

RemediationAI

A vendor patch is available. Apply the latest security update as soon as possible. Apply vendor patches when available. Implement network segmentation and monitoring as interim mitigations.