CVE-2024-58400

llama.cpp before b3701 contains an out-of-bounds read vulnerability in llama_decode_internal and llama_encode_internal that allows remote unauthenticated attackers to read memory by supplying unvalidated token IDs. Attackers can send integer-array prompts to the llama-server /completion endpoint with IDs outside 0 to n_vocab to read embedding memory out of bounds or crash the process.

CVSS v3 8.2 HIGH

8.2^/10

CVSS v3 : HIGH

Vector :

Exploitability : 3.9 / Impact : 4.2

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction NONE

Confidentiality Impact LOW

Integrity Impact NONE

Availability Impact HIGH

Scope UNCHANGED

References

Link	Resource
https://github.com/ggml-org/llama.cpp/blob/b3681/examples/server/server.cpp#L789
https://github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9327fe
https://github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e8acd3
https://github.com/ggml-org/llama.cpp/pull/9359
https://github.com/ggml-org/llama.cpp/releases/tag/b3701
https://www.vulncheck.com/advisories/llama-cpp-before-b3701-out-of-bounds-read-in-llama-decode-via-token-ids

Configurations

No configuration.

History

27 Oct 2026, 23:10

Type	Values Removed	Values Added
Summary		(es) llama.cpp versiones anteriores a b3701 contiene una vulnerabilidad de lectura fuera de límites en llama_decode_internal y llama_encode_internal que permite a atacantes remotos no autenticados leer memoria suministrando IDs de token no validados. Los atacantes pueden enviar prompts de matrices de enteros al endpoint /completion del servidor llama?server con IDs fuera del rango 0 a n_vocab para leer la memoria de incrustaciones fuera de límites o provocar el bloqueo del proceso.

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-2024-58400

Mitre link : CVE-2024-58400

CVE.ORG link : CVE-2024-58400

JSON object : View

Products Affected

No product.

CWE

CWE-129

Improper Validation of Array Index

{"id": "CVE-2024-58400", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2024-58400", "role": "CISA Coordinator", "options": [{"exploitation": "none"}, {"automatable": "yes"}, {"technicalImpact": "partial"}], "version": "2.0.3", "timestamp": "2026-10-27T13:46:15.115363Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 8.2, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H", "integrityImpact": "NONE", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "LOW"}, "impactScore": 4.2, "exploitabilityScore": 3.9}], "cvssMetricV40": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 8.8, "Automatable": "NOT_DEFINED", "attackVector": "NETWORK", "baseSeverity": "HIGH", "valueDensity": "NOT_DEFINED", "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/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": "NONE", "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": "0", "lessThan": "b3701", "versionType": "custom"}], "packageURL": "pkg:github/ggml-org/llama.cpp", "defaultStatus": "unaffected"}]}], "published": "2026-10-27T01:19:03.080", "references": [{"url": "https://github.com/ggml-org/llama.cpp/blob/b3681/examples/server/server.cpp#L789", "source": "disclosure@vulncheck.com"}, {"url": "https://github.com/ggml-org/llama.cpp/commit/eae597182cb61bbde0b26e7cec5999d28b9327fe", "source": "disclosure@vulncheck.com"}, {"url": "https://github.com/ggml-org/llama.cpp/commit/faf69d4237c9ae4d7f572b4674d1002463e8acd3", "source": "disclosure@vulncheck.com"}, {"url": "https://github.com/ggml-org/llama.cpp/pull/9359", "source": "disclosure@vulncheck.com"}, {"url": "https://github.com/ggml-org/llama.cpp/releases/tag/b3701", "source": "disclosure@vulncheck.com"}, {"url": "https://www.vulncheck.com/advisories/llama-cpp-before-b3701-out-of-bounds-read-in-llama-decode-via-token-ids", "source": "disclosure@vulncheck.com"}], "vulnStatus": "Awaiting Analysis", "weaknesses": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "description": [{"lang": "en", "value": "CWE-129"}]}], "descriptions": [{"lang": "en", "value": "llama.cpp before b3701 contains an out-of-bounds read vulnerability in llama_decode_internal and llama_encode_internal that allows remote unauthenticated attackers to read memory by supplying unvalidated token IDs. Attackers can send integer-array prompts to the llama-server /completion endpoint with IDs outside 0 to n_vocab to read embedding memory out of bounds or crash the process."}, {"lang": "es", "value": "llama.cpp versiones anteriores a b3701 contiene una vulnerabilidad de lectura fuera de l\u00edmites en llama_decode_internal y llama_encode_internal que permite a atacantes remotos no autenticados leer memoria suministrando IDs de token no validados. Los atacantes pueden enviar prompts de matrices de enteros al endpoint /completion del servidor llama?server con IDs fuera del rango 0 a n_vocab para leer la memoria de incrustaciones fuera de l\u00edmites o provocar el bloqueo del proceso."}], "lastModified": "2026-10-27T23:10:00.153", "sourceIdentifier": "disclosure@vulncheck.com"}