CVE-2025-62372
Description
A denial-of-service vulnerability in vLLM allows an attacker with API access to crash the engine by submitting multimodal embedding tensors that have the correct number of dimensions but an invalid internal shape. Because vLLM validates only the tensor’s ndim and not the full expected shape, malformed embeddings trigger shape mismatches or validation failures during processing, causing the inference engine to terminate.
Statement
This flaw is rated Moderate rather than Important because its impact is strictly limited to availability and requires low but existing privileges to exploit. The issue arises from incomplete shape validation of multimodal embedding tensors, which can cause deterministic crashes in the inference engine, but it does not enable memory corruption, data leakage, integrity compromise, or execution of arbitrary code. Exploitation requires an authenticated or API-key-holding user to submit malformed multimodal inputs, meaning it cannot be triggered by an unauthenticated attacker on an exposed endpoint. Additionally, the failure mode is a clean crash rather than undefined behavior, so the blast radius is constrained to service interruption rather than broader systemic compromise. These factors—PR:L requirement, no confidentiality/integrity impact, deterministic failure mode, and scoped DoS only—technically align the issue with Moderate severity instead of an Important flaw.
Mitigation
No mitigation is currently available that meets Red Hat Product Security’s standards for usability, deployment, applicability, or stability.
Common Vulnerability Scoring System (CVSS) Score Details
Info alert:Important note
CVSS scores for open source components depend on vendor-specific factors (e.g. version or build chain). Therefore, Red Hat's score and impact rating can be different from NVD and other vendors. Red Hat remains the authoritative CVE Naming Authority (CNA) source for its products and services (see Red Hat classifications).
CVSS v3 Score Breakdown
| Red Hat | NVD | cve.org | |
|---|---|---|---|
| Base Score | 6.5 | 6.5 | N/A |
| Attack Vector | Network | Network | N/A |
| Attack Complexity | Low | Low | N/A |
| Privileges Required | Low | Low | N/A |
| User Interaction | None | None | N/A |
| Scope | Unchanged | Unchanged | N/A |
| Confidentiality | None | None | N/A |
| Integrity Impact | None | None | N/A |
| Availability Impact | High | High | N/A |
Vector
Red Hat: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
NVD: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Understanding the Weakness (CWE)
Integrity,Availability
Technical Impact: DoS: Crash, Exit, or Restart
Use of an index that is outside the bounds of an array will very likely result in the corruption of relevant memory and perhaps instructions, leading to a crash, if the values are outside of the valid memory area.
Integrity
Technical Impact: Modify Memory
If the memory corrupted is data, rather than instructions, the system will continue to function with improper values.
Confidentiality,Integrity
Technical Impact: Modify Memory; Read Memory
Use of an index that is outside the bounds of an array can also trigger out-of-bounds read or write operations, or operations on the wrong objects; i.e., "buffer overflows" are not always the result. This may result in the exposure or modification of sensitive data.
Integrity,Confidentiality,Availability
Technical Impact: Execute Unauthorized Code or Commands
If the memory accessible by the attacker can be effectively controlled, it may be possible to execute arbitrary code, as with a standard buffer overflow and possibly without the use of large inputs if a precise index can be controlled.
Integrity,Availability,Confidentiality
Technical Impact: DoS: Crash, Exit, or Restart; Execute Unauthorized Code or Commands; Read Memory; Modify Memory
A single fault could allow either an overflow (CWE-788) or underflow (CWE-786) of the array index. What happens next will depend on the type of operation being performed out of bounds, but can expose sensitive information, cause a system crash, or possibly lead to arbitrary code execution.
Frequently Asked Questions
Not sure what something means? Check out our Security Glossary.
Want to get errata notifications? Sign up here.
