CVE-2026-33298 (GCVE-0-2026-33298)
Vulnerability from cvelistv5 – Published: 2026-03-24 00:01 – Updated: 2026-03-25 03:55
VLAI?
Title
llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing
Summary
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.
Severity ?
7.8 (High)
Assigner
References
| URL | Tags | |||||||
|---|---|---|---|---|---|---|---|---|
|
||||||||
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-33298",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-03-24T00:00:00+00:00",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-03-25T03:55:51.679Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "llama.cpp",
"vendor": "ggml-org",
"versions": [
{
"status": "affected",
"version": "\u003c b7824"
}
]
}
],
"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."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "HIGH",
"baseScore": 7.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-122",
"description": "CWE-122: Heap-based Buffer Overflow",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-190",
"description": "CWE-190: Integer Overflow or Wraparound",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-03-24T00:01:40.989Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-96jg-mvhq-q7q7",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-96jg-mvhq-q7q7"
},
{
"name": "https://github.com/ggml-org/llama.cpp/releases/tag/b7824",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/ggml-org/llama.cpp/releases/tag/b7824"
}
],
"source": {
"advisory": "GHSA-96jg-mvhq-q7q7",
"discovery": "UNKNOWN"
},
"title": "llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-33298",
"datePublished": "2026-03-24T00:01:40.989Z",
"dateReserved": "2026-03-18T18:55:47.427Z",
"dateUpdated": "2026-03-25T03:55:51.679Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-33298",
"date": "2026-04-23",
"epss": "0.00015",
"percentile": "0.03335"
},
"nvd": "{\"cve\":{\"id\":\"CVE-2026-33298\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-03-24T01:17:01.870\",\"lastModified\":\"2026-03-24T15:53:48.067\",\"vulnStatus\":\"Awaiting Analysis\",\"cveTags\":[],\"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.\"}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H\",\"baseScore\":7.8,\"baseSeverity\":\"HIGH\",\"attackVector\":\"LOCAL\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"REQUIRED\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":1.8,\"impactScore\":5.9}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-122\"},{\"lang\":\"en\",\"value\":\"CWE-190\"}]}],\"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\"}]}}",
"vulnrichment": {
"containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-33298\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-03-24T13:30:06.212447Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-03-24T13:30:16.553Z\"}}], \"cna\": {\"title\": \"llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing\", \"source\": {\"advisory\": \"GHSA-96jg-mvhq-q7q7\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"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\"}}], \"affected\": [{\"vendor\": \"ggml-org\", \"product\": \"llama.cpp\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c b7824\"}]}], \"references\": [{\"url\": \"https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-96jg-mvhq-q7q7\", \"name\": \"https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-96jg-mvhq-q7q7\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/ggml-org/llama.cpp/releases/tag/b7824\", \"name\": \"https://github.com/ggml-org/llama.cpp/releases/tag/b7824\", \"tags\": [\"x_refsource_MISC\"]}], \"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.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-122\", \"description\": \"CWE-122: Heap-based Buffer Overflow\"}]}, {\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-190\", \"description\": \"CWE-190: Integer Overflow or Wraparound\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-03-24T00:01:40.989Z\"}}}",
"cveMetadata": "{\"cveId\": \"CVE-2026-33298\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-03-25T03:55:51.679Z\", \"dateReserved\": \"2026-03-18T18:55:47.427Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-03-24T00:01:40.989Z\", \"assignerShortName\": \"GitHub_M\"}",
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Sightings
| Author | Source | Type | Date |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Loading…
Loading…