CVE-2026-33298

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.

CVSS v3 7.8 HIGH

7.8^/10

CVSS v3 : HIGH

Vector :

Exploitability : 1.8 / Impact : 5.9

Attack Vector LOCAL

Attack Complexity LOW

Privileges Required NONE

User Interaction REQUIRED

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact HIGH

Scope UNCHANGED

References

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

Configurations

No configuration.

History

No history.

Information

Published : 2026-03-24 01:17

Updated : 2026-03-24 15:53

NVD link : CVE-2026-33298

Mitre link : CVE-2026-33298

CVE.ORG link : CVE-2026-33298

JSON object : View

Products Affected

No product.

CWE

CWE-122

Heap-based Buffer Overflow

CWE-190

Integer Overflow or Wraparound

{"id": "CVE-2026-33298", "cveTags": [], "metrics": {"cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 7.8, "attackVector": "LOCAL", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "REQUIRED", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 5.9, "exploitabilityScore": 1.8}]}, "published": "2026-03-24T01:17:01.870", "references": [{"url": "https://github.com/ggml-org/llama.cpp/releases/tag/b7824", "source": "security-advisories@github.com"}, {"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-96jg-mvhq-q7q7", "source": "security-advisories@github.com"}], "vulnStatus": "Awaiting Analysis", "weaknesses": [{"type": "Primary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-122"}, {"lang": "en", "value": "CWE-190"}]}], "descriptions": [{"lang": "en", "value": "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."}, {"lang": "es", "value": "llama.cpp es una inferencia de varios modelos LLM en C/C++. Antes de b7824, una vulnerabilidad de desbordamiento de entero en la funci\u00f3n `ggml_nbytes` permite a un atacante eludir la validaci\u00f3n de memoria al crear un archivo GGUF con dimensiones de tensor espec\u00edficas. Esto hace que `ggml_nbytes` devuelva un tama\u00f1o significativamente menor al requerido (por ejemplo, 4MB en lugar de Exabytes), lo que lleva a un desbordamiento de b\u00fafer basado en mont\u00edculo cuando la aplicaci\u00f3n procesa posteriormente el tensor. Esta vulnerabilidad permite una posible ejecuci\u00f3n remota de c\u00f3digo (RCE) a trav\u00e9s de corrupci\u00f3n de memoria. b7824 contiene una correcci\u00f3n."}], "lastModified": "2026-03-24T15:53:48.067", "sourceIdentifier": "security-advisories@github.com"}