CVE-2024-32878

Llama.cpp is LLM inference in C/C++. There is a use of uninitialized heap variable vulnerability in gguf_init_from_file, the code will free this uninitialized variable later. In a simple POC, it will directly cause a crash. If the file is carefully constructed, it may be possible to control this uninitialized value and cause arbitrary address free problems. This may further lead to be exploited. Causes llama.cpp to crash (DoS) and may even lead to arbitrary code execution (RCE). This vulnerability has been patched in commit b2740.

CVSS v3 7.1 HIGH

7.1^/10

CVSS v3 : HIGH

Vector :

Exploitability : 1.6 / Impact : 5.5

Attack Vector NETWORK

Attack Complexity HIGH

Privileges Required NONE

User Interaction REQUIRED

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact LOW

Scope UNCHANGED

References

Link	Resource
https://github.com/ggerganov/llama.cpp/releases/tag/b2749	Release Notes
https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv	Vendor Advisory
https://github.com/ggerganov/llama.cpp/releases/tag/b2749	Release Notes
https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv	Vendor Advisory

Configurations

Configuration 1 (hide)

cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*

History

02 Sep 2025, 18:30

Type	Values Removed	Values Added
CPE		cpe:2.3:a:ggml:llama.cpp::::::::
References	~~() https://github.com/ggerganov/llama.cpp/releases/tag/b2749 -~~	() https://github.com/ggerganov/llama.cpp/releases/tag/b2749 - Release Notes
References	~~() https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv -~~	() https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv - Vendor Advisory
First Time		Ggml Ggml llama.cpp

Information

Published : 2024-04-26 21:15

Updated : 2025-09-02 18:30

NVD link : CVE-2024-32878

Mitre link : CVE-2024-32878

CVE.ORG link : CVE-2024-32878

JSON object : View

Products Affected

ggml

llama.cpp

CWE

CWE-456

Missing Initialization of a Variable

{"id": "CVE-2024-32878", "cveTags": [], "metrics": {"cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 7.1, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:L", "integrityImpact": "HIGH", "userInteraction": "REQUIRED", "attackComplexity": "HIGH", "availabilityImpact": "LOW", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 5.5, "exploitabilityScore": 1.6}, {"type": "Primary", "source": "nvd@nist.gov", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 8.8, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/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": 2.8}]}, "published": "2024-04-26T21:15:49.260", "references": [{"url": "https://github.com/ggerganov/llama.cpp/releases/tag/b2749", "tags": ["Release Notes"], "source": "security-advisories@github.com"}, {"url": "https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv", "tags": ["Vendor Advisory"], "source": "security-advisories@github.com"}, {"url": "https://github.com/ggerganov/llama.cpp/releases/tag/b2749", "tags": ["Release Notes"], "source": "af854a3a-2127-422b-91ae-364da2661108"}, {"url": "https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv", "tags": ["Vendor Advisory"], "source": "af854a3a-2127-422b-91ae-364da2661108"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-456"}]}], "descriptions": [{"lang": "en", "value": "Llama.cpp is LLM inference in C/C++. There is a use of uninitialized heap variable vulnerability in gguf_init_from_file, the code will free this uninitialized variable later. In a simple POC, it will directly cause a crash. If the file is carefully constructed, it may be possible to control this uninitialized value and cause arbitrary address free problems. This may further lead to be exploited. Causes llama.cpp to crash (DoS) and may even lead to arbitrary code execution (RCE). This vulnerability has been patched in commit b2740.\n"}, {"lang": "es", "value": "Llama.cpp es una inferencia LLM en C/C++. Hay un uso de vulnerabilidad de variable de mont\u00f3n no inicializada en gguf_init_from_file, el c\u00f3digo liberar\u00e1 esta variable no inicializada m\u00e1s adelante. En una POC simple, provocar\u00e1 directamente un bloqueo. Si el archivo se construye cuidadosamente, es posible controlar este valor no inicializado y causar problemas sin direcciones arbitrarias. Esto puede llevar a\u00fan m\u00e1s a ser explotado. Provoca que llama.cpp falle (DoS) e incluso puede provocar la ejecuci\u00f3n de c\u00f3digo arbitrario (RCE). Esta vulnerabilidad ha sido parcheada en el commit b2740."}], "lastModified": "2025-09-02T18:30:15.713", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "26E87746-7267-4255-B93E-3935A6A85278", "versionEndExcluding": "b2740", "versionStartIncluding": "b2715"}], "operator": "OR"}]}], "sourceIdentifier": "security-advisories@github.com"}