> CVE-2026-33298 [HIGH]

« BACK_TO_HOME
PUBLISHED
2026-03-24 01:17
MODIFIED
2026-03-24 01:17
CVSS_SCORE V3
7.8
EPSS (Prob. Exploit)
0.50%
Top 57.2%
DATA SOURCES:
NVD đź”— 2026-03-24 CWE MITRE đź”— 2026-11-01 FIRST EPSS đź”— 2026-11-08 OSV đź”— 2026-11-01

> DESCRIPTION

llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the `ggml_nbytes` function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes `ggml_nbytes` to return a significantly smaller size than required (e.g., 4MB instead of Exabytes), leading to a heap-based buffer overflow when the application subsequently processes the tensor. This vulnerability allows potential Remote Code Execution (RCE) via memory corruption. b7824 contains a fix.

> 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:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
EXPLOITABILITY
1.8
IMPACT
5.9

> MÉTRIQUES CVSS DÉTAILLÉES

CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Métrique Valeur Interprétation
AV (Vecteur d'Attaque)
Attack Vector
Local (L)
Exploit nécessite un accès local au système
AC (Complexité d'Attaque)
Attack Complexity
Low (L)
Peu de conditions requises pour exploiter
PR (Privilèges Requis)
Privileges Required
None (N)
Aucune authentification requise
UI (Interaction Utilisateur)
User Interaction
Required (R)
Nécessite une action utilisateur (clic lien, ouverture fichier, etc.)
S (Périmètre)
Scope
Unchanged (U)
Impact reste dans le périmètre du composant compromis
C (Impact Confidentialité)
Confidentiality Impact
High (H)
Divulgation totale d'informations
I (Impact Intégrité)
Integrity Impact
High (H)
Modification totale des données possible
A (Impact Disponibilité)
Availability Impact
High (H)
Interruption totale du service possible

> RÉSUMÉ DES IMPACTS

Confidentialité
High
Divulgation totale d'informations
Intégrité
High
Modification totale des données possible
Disponibilité
High
Interruption totale du service possible

> WEAKNESSES

CWE-122 CWE-190

> CWE DETAILED DESCRIPTIONS

CWE-122: Heap-based Buffer Overflow - The product writes past the end of a buffer that was allocated on the heap. | CWE-190: Integer Overflow or Wraparound - The product performs a calculation that can produce an integer overflow or wraparound when the logic assumes that the resulting value will always be larger than the original value. This occurs when an integer value is incremented to a value that is too large to store in the associated representation. When this occurs, the value may become a very small or negative number.

> OSV (GOOGLE OPEN SOURCE VULNERABILITIES)

llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing

AFFECTED PACKAGES:
Unknown / Unknown
5314 versions affected
ALIASES:
GHSA-96jg-mvhq-q7q7

> HISTORIQUE DES MODIFICATIONS

Première apparition
24/03/2026 01:17
Source: NVD
📊 ENRICHISSEMENT 01/11/2026 06:59
CWE
Champ modifié: Description CWE
Ancienne valeur:
CWE-122: Heap-based Buffer Overflow - A heap overflow condition is a buffer overflow, where the buffer that can be overwritten is allocated in the heap portion of memory, generally meaning that the bu...
Nouvelle valeur:
CWE-122: Heap-based Buffer Overflow - The product writes past the end of a buffer that was allocated on the heap. | CWE-190: Integer Overflow or Wraparound - The product performs a calculation that ca...
📊 ENRICHISSEMENT 01/04/2026 06:02
CWE
Champ modifié: Description CWE
Ancienne valeur:
N/A
Nouvelle valeur:
CWE-122: Heap-based Buffer Overflow - A heap overflow condition is a buffer overflow, where the buffer that can be overwritten is allocated in the heap portion of memory, generally meaning that the bu...
Total des modifications: 2 Dernière mise à jour: 1 week ago

> REFERENCES

https://github.com/ggml-org/llama.cpp/releases/tag/b7824
https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-96jg-mvhq-q7q7
« BACK_TO_HOME