CVE-2024-58399

llama.cpp before b2731 contains an out-of-bounds read vulnerability in llama_model_loader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the process or load adjacent process memory as model weights.

CVSS v3 6.1 MEDIUM

6.1^/10

CVSS v3 : MEDIUM

Vector :

Exploitability : 1.8 / Impact : 4.2

Attack Vector LOCAL

Attack Complexity LOW

Privileges Required NONE

User Interaction REQUIRED

Confidentiality Impact LOW

Integrity Impact NONE

Availability Impact HIGH

Scope UNCHANGED

References

Link	Resource
https://github.com/ggml-org/llama.cpp/blob/b2730/llama.cpp#L3002-L3004
https://github.com/ggml-org/llama.cpp/commit/0ead1f1072fdc70720f92e008a294dc74a826b1d
https://github.com/ggml-org/llama.cpp/issues/6774
https://github.com/ggml-org/llama.cpp/pull/6885
https://github.com/ggml-org/llama.cpp/releases/tag/b2731
https://www.vulncheck.com/advisories/llama-cpp-before-b2731-out-of-bounds-read-via-gguf-tensor-offsets

Configurations

No configuration.

History

27 Oct 2026, 23:10

Type	Values Removed	Values Added
Summary		(es) llama.cpp antes de la versión b2731 contiene una vulnerabilidad de lectura fuera de límites en llama_model_loader que permite a los atacantes leer memoria fuera del archivo de modelo mapeado mediante desplazamientos de tensor GGUF manipulados. Los atacantes pueden suministrar un archivo de modelo GGUF manipulado o truncado con desplazamientos de tensor de 64?bits arbitrarios para bloquear el proceso o cargar la memoria adyacente del proceso como pesos del modelo.

27 Oct 2026, 01:19

Type	Values Removed	Values Added
New CVE

Information

Published : 2026-10-27 01:19

Updated : 2026-10-27 23:10

NVD link : CVE-2024-58399

Mitre link : CVE-2024-58399

CVE.ORG link : CVE-2024-58399

JSON object : View

Products Affected

No product.

CWE

CWE-125

Out-of-bounds Read

{"id": "CVE-2024-58399", "cveTags": [], "metrics": {"cvssMetricV31": [{"type": "Primary", "source": "disclosure@vulncheck.com", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 6.1, "attackVector": "LOCAL", "baseSeverity": "MEDIUM", "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:N/A:H", "integrityImpact": "NONE", "userInteraction": "REQUIRED", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "LOW"}, "impactScore": 4.2, "exploitabilityScore": 1.8}], "cvssMetricV40": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 6.9, "Automatable": "NOT_DEFINED", "attackVector": "LOCAL", "baseSeverity": "MEDIUM", "valueDensity": "NOT_DEFINED", "vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:L/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X", "exploitMaturity": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "userInteraction": "PASSIVE", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "NONE", "subIntegrityImpact": "NONE", "vulnIntegrityImpact": "NONE", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "NONE", "vulnAvailabilityImpact": "HIGH", "availabilityRequirement": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "subConfidentialityImpact": "NONE", "vulnConfidentialityImpact": "LOW", "confidentialityRequirement": "NOT_DEFINED", "modifiedAttackRequirements": "NOT_DEFINED", "modifiedPrivilegesRequired": "NOT_DEFINED", "modifiedSubIntegrityImpact": "NOT_DEFINED", "modifiedVulnIntegrityImpact": "NOT_DEFINED", "vulnerabilityResponseEffort": "NOT_DEFINED", "modifiedSubAvailabilityImpact": "NOT_DEFINED", "modifiedVulnAvailabilityImpact": "NOT_DEFINED", "modifiedSubConfidentialityImpact": "NOT_DEFINED", "modifiedVulnConfidentialityImpact": "NOT_DEFINED"}}]}, "affected": [{"source": "disclosure@vulncheck.com", "affectedData": [{"vendor": "ggml-org", "product": "llama.cpp", "versions": [{"status": "affected", "version": "b1046", "lessThan": "b2731", "versionType": "custom"}], "packageURL": "pkg:github/ggml-org/llama.cpp", "defaultStatus": "unaffected"}]}], "published": "2026-10-27T01:19:02.810", "references": [{"url": "https://github.com/ggml-org/llama.cpp/blob/b2730/llama.cpp#L3002-L3004", "source": "disclosure@vulncheck.com"}, {"url": "https://github.com/ggml-org/llama.cpp/commit/0ead1f1072fdc70720f92e008a294dc74a826b1d", "source": "disclosure@vulncheck.com"}, {"url": "https://github.com/ggml-org/llama.cpp/issues/6774", "source": "disclosure@vulncheck.com"}, {"url": "https://github.com/ggml-org/llama.cpp/pull/6885", "source": "disclosure@vulncheck.com"}, {"url": "https://github.com/ggml-org/llama.cpp/releases/tag/b2731", "source": "disclosure@vulncheck.com"}, {"url": "https://www.vulncheck.com/advisories/llama-cpp-before-b2731-out-of-bounds-read-via-gguf-tensor-offsets", "source": "disclosure@vulncheck.com"}], "vulnStatus": "Awaiting Analysis", "weaknesses": [{"type": "Primary", "source": "disclosure@vulncheck.com", "description": [{"lang": "en", "value": "CWE-125"}]}], "descriptions": [{"lang": "en", "value": "llama.cpp before b2731 contains an out-of-bounds read vulnerability in llama_model_loader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the process or load adjacent process memory as model weights."}, {"lang": "es", "value": "llama.cpp antes de la versi\u00f3n b2731 contiene una vulnerabilidad de lectura fuera de l\u00edmites en llama_model_loader que permite a los atacantes leer memoria fuera del archivo de modelo mapeado mediante desplazamientos de tensor GGUF manipulados. Los atacantes pueden suministrar un archivo de modelo GGUF manipulado o truncado con desplazamientos de tensor de 64?bits arbitrarios para bloquear el proceso o cargar la memoria adyacente del proceso como pesos del modelo."}], "lastModified": "2026-10-27T23:10:00.153", "sourceIdentifier": "disclosure@vulncheck.com"}