CVE-2025-62372 Vulnerability Analysis & Exploit Details

CVE-2025-62372
Vulnerability Scoring

Analysis In Progress
Analysis In Progress

Attack Complexity Details

  • Attack Complexity:
    Attack Complexity Analysis In Progress
  • Attack Vector:
    Attack Vector Under Analysis
  • Privileges Required: None
    No authentication is required for exploitation.
  • Scope:
    Impact is confined to the initially vulnerable component.
  • User Interaction: None
    No user interaction is necessary for exploitation.

CVE-2025-62372 Details

Status: Received on 21 Nov 2025, 02:15 UTC

Published on: 21 Nov 2025, 02:15 UTC

CVSS Release:

CVE-2025-62372 Vulnerability Summary

CVE-2025-62372: vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct ndim but incorrect shape (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page). This issue has been patched in version 0.11.1.

Assessing the Risk of CVE-2025-62372

Access Complexity Graph

The exploitability of CVE-2025-62372 depends on two key factors: attack complexity (the level of effort required to execute an exploit) and privileges required (the access level an attacker needs).

Exploitability Analysis for CVE-2025-62372

No exploitability data is available for CVE-2025-62372.

Understanding AC and PR

A lower complexity and fewer privilege requirements make exploitation easier. Security teams should evaluate these aspects to determine the urgency of mitigation strategies, such as patch management and access control policies.

Attack Complexity (AC) measures the difficulty in executing an exploit. A high AC means that specific conditions must be met, making an attack more challenging, while a low AC means the vulnerability can be exploited with minimal effort.

Privileges Required (PR) determine the level of system access necessary for an attack. Vulnerabilities requiring no privileges are more accessible to attackers, whereas high privilege requirements limit exploitation to authorized users with elevated access.

CVSS Score Breakdown Chart

Above is the CVSS Sub-score Breakdown for CVE-2025-62372, illustrating how Base, Impact, and Exploitability factors combine to form the overall severity rating. A higher sub-score typically indicates a more severe or easier-to-exploit vulnerability.

CIA Impact Analysis

Below is the Impact Analysis for CVE-2025-62372, showing how Confidentiality, Integrity, and Availability might be affected if the vulnerability is exploited. Higher values usually signal greater potential damage.

  • Confidentiality: None
    CVE-2025-62372 does not compromise confidentiality.
  • Integrity: None
    CVE-2025-62372 does not impact data integrity.
  • Availability: None
    CVE-2025-62372 does not affect system availability.

CVE-2025-62372 References

External References

CWE Common Weakness Enumeration

CWE-129

CAPEC Common Attack Pattern Enumeration and Classification

  • Overflow Buffers CAPEC-100 Buffer Overflow attacks target improper or missing bounds checking on buffer operations, typically triggered by input injected by an adversary. As a consequence, an adversary is able to write past the boundaries of allocated buffer regions in memory, causing a program crash or potentially redirection of execution as per the adversaries' choice.

Protect Your Infrastructure against CVE-2025-62372: Combat Critical CVE Threats

Stay updated with real-time CVE vulnerabilities and take action to secure your systems. Enhance your cybersecurity posture with the latest threat intelligence and mitigation techniques. Develop the skills necessary to defend against CVEs and secure critical infrastructures. Join the top cybersecurity professionals safeguarding today's infrastructures.

Other 5 Recently Published CVEs Vulnerabilities

  • CVE-2025-64310 – EPSON WebConfig and Epson Web Control for SEIKO EPSON Projector Products do not restrict excessive authentication attempts. An administrative user'...
  • CVE-2025-64762 – The AuthKit library for Next.js provides convenient helpers for authentication and session management using WorkOS & AuthKit with Next.js. In authk...
  • CVE-2025-64755 – Claude Code is an agentic coding tool. Prior to version 2.0.31, due to an error in sed command parsing, it was possible to bypass the Claude Code r...
  • CVE-2025-64751 – OpenFGA is a high-performance and flexible authorization/permission engine built for developers and inspired by Google Zanzibar. OpenFGA v1.4.0 to ...
  • CVE-2025-62426 – vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokeni...