> CVE-2026-44223 [MEDIUM]

« BACK_TO_HOME
PUBLISHED
2026-05-12 20:16
MODIFIED
2026-05-12 20:16
CVSS_SCORE V3
6.5
EPSS (Prob. Exploit)
0.37%
Top 69.4%
DATA SOURCES:
NVD 🔗 2026-05-12 CWE MITRE 🔗 2026-11-01 FIRST EPSS 🔗 2026-11-01 GITHUB 🔗 2026-11-05 OSV 🔗 2026-11-02

> DESCRIPTION

vLLM is an inference and serving engine for large language models (LLMs). From to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., "repetition_penalty": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0.

> AFFECTED_PRODUCTS

ℹ️ Aucun produit affecté n'a encore été publié par NVD pour cette CVE.

> CVSS V3 METRICS

CVSS_VECTOR
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
EXPLOITABILITY
2.8
IMPACT
3.6

> MÉTRIQUES CVSS DÉTAILLÉES

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Métrique Valeur Interprétation
AV (Vecteur d'Attaque)
Attack Vector
Network (N)
Exploit possible à distance via réseau (HTTP, API, etc.)
AC (Complexité d'Attaque)
Attack Complexity
Low (L)
Peu de conditions requises pour exploiter
PR (Privilèges Requis)
Privileges Required
Low (L)
Authentifié avec compte utilisateur basique
UI (Interaction Utilisateur)
User Interaction
None (N)
Aucune interaction utilisateur nécessaire
S (Périmètre)
Scope
Unchanged (U)
Impact reste dans le périmètre du composant compromis
C (Impact Confidentialité)
Confidentiality Impact
None (N)
Aucune divulgation d'informations
I (Impact Intégrité)
Integrity Impact
None (N)
Aucune modification de données possible
A (Impact Disponibilité)
Availability Impact
High (H)
Interruption totale du service possible

> RÉSUMÉ DES IMPACTS

Confidentialité
None
Aucune divulgation d'informations
Intégrité
None
Aucune modification de données possible
Disponibilité
High
Interruption totale du service possible

> WEAKNESSES

CWE-131 CWE-704

> CWE DETAILED DESCRIPTIONS

CWE-131: Incorrect Calculation of Buffer Size - The product does not correctly calculate the size to be used when allocating a buffer. | CWE-704: Incorrect Type Conversion or Cast - The product does not correctly convert an object, resource, or structure from one type to a different type.

> RED HAT SECURITY ADVISORIES

Red Hat Security Advisory: Red Hat AI Inference 3.4.4 (rocm)
Red Hat AI Inference 3.4.4 (rocm) is now available.
Red Hat Security Advisory: Red Hat AI Inference 3.4.4 (cuda)
Red Hat AI Inference 3.4.4 (cuda) is now available.
Red Hat Security Advisory: Red Hat AI Inference 3.4.4 (spyre)
Red Hat AI Inference 3.4.4 (spyre) is now available.
Red Hat Security Advisory: Red Hat AI Inference 3.4.4 (cpu)
Red Hat AI Inference 3.4.4 (cpu) is now available.
Red Hat Security Advisory: Red Hat Enterprise Linux AI 3.4.4 enhancement update
Updated Red Hat Enterprise Linux AI 3.4.4 container images are now available.
Red Hat Security Advisory: Red Hat Enterprise Linux AI 3.4.4 enhancement update
Updated Red Hat Enterprise Linux AI 3.4.4 container disk images are now available.
Red Hat Security Advisory: Red Hat AI Inference 3.4.5 (rocm)
Red Hat AI Inference 3.4.5 (rocm) is now available.
Red Hat Security Advisory: Red Hat AI Inference 3.4.5 (cuda)
Red Hat AI Inference 3.4.5 (cuda) is now available.
Red Hat Security Advisory: Red Hat AI Inference 3.4.5 (cpu)
Red Hat AI Inference 3.4.5 (cpu) is now available.
Red Hat Security Advisory: Red Hat AI Inference 3.4.5 (spyre)
Red Hat AI Inference 3.4.5 (spyre) is now available.
Red Hat Security Advisory: Red Hat AI Inference 3.4.5 (rocm)
Red Hat AI Inference 3.4.5 (rocm) is now available.
Red Hat Security Advisory: Red Hat AI Inference 3.4.5 (cuda)
Red Hat AI Inference 3.4.5 (cuda) is now available.
Red Hat Security Advisory: Red Hat AI Inference 3.4.5 (spyre)
Red Hat AI Inference 3.4.5 (spyre) is now available.
Red Hat Security Advisory: Red Hat AI Inference 3.4.5 (cpu)
Red Hat AI Inference 3.4.5 (cpu) is now available.

> GITHUB SECURITY ADVISORY

GHSA-83vm-p52w-f9pw MODERATE

vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters

AFFECTED PACKAGES:
PIP / vllm
>= 0.18.0, < 0.20.0
Fixed in: 0.20.0

> OSV (GOOGLE OPEN SOURCE VULNERABILITIES)

vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters

AFFECTED PACKAGES:
Unknown / Unknown
ALIASES:
GHSA-83vm-p52w-f9pw, PYSEC-2026-145

> HISTORIQUE DES MODIFICATIONS

Première apparition
12/05/2026 20:16
Source: NVD
📊 ENRICHISSEMENT 01/11/2026 06:59
CWE
Champ modifié: Description CWE
Ancienne valeur:
CWE-131: Incorrect Calculation of Buffer Size - The product does not correctly calculate the size to be used when allocating a buffer, which could lead to a buffer overflow. | CWE-704: Incorrect Type ...
Nouvelle valeur:
CWE-131: Incorrect Calculation of Buffer Size - The product does not correctly calculate the size to be used when allocating a buffer. | CWE-704: Incorrect Type Conversion or Cast - The product does n...
📊 ENRICHISSEMENT 01/06/2026 06:01
CWE
Champ modifié: Description CWE
Ancienne valeur:
N/A
Nouvelle valeur:
CWE-131: Incorrect Calculation of Buffer Size - The product does not correctly calculate the size to be used when allocating a buffer, which could lead to a buffer overflow. | CWE-704: Incorrect Type ...
Total des modifications: 2 Dernière mise à jour: 6 days ago

> REFERENCES

https://github.com/vllm-project/vllm/pull/38610
https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw
« BACK_TO_HOME