Vulnerabilites related to ggml - llama.cpp
CVE-2024-41130 (GCVE-0-2024-41130)
Vulnerability from cvelistv5
Published
2024-07-22 17:28
Modified
2024-08-02 04:46
Severity ?
VLAI Severity ?
EPSS score ?
CWE
- CWE-476 - NULL Pointer Dereference
Summary
llama.cpp provides LLM inference in C/C++. Prior to b3427, llama.cpp contains a null pointer dereference in gguf_init_from_file. This vulnerability is fixed in b3427.
References
| ▼ | URL | Tags |
|---|---|---|
| https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-49q7-2jmh-92fp | x_refsource_CONFIRM | |
| https://github.com/ggerganov/llama.cpp/commit/07283b1a90e1320aae4762c7e03c879043910252 | x_refsource_MISC |
{
"containers": {
"adp": [
{
"affected": [
{
"cpes": [
"cpe:2.3:a:ggerganov:llama.cpp:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unknown",
"product": "llama.cpp",
"vendor": "ggerganov",
"versions": [
{
"lessThan": "b3427",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"other": {
"content": {
"id": "CVE-2024-41130",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-07-22T17:50:21.616281Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2024-07-22T17:51:55.310Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
},
{
"providerMetadata": {
"dateUpdated": "2024-08-02T04:46:51.141Z",
"orgId": "af854a3a-2127-422b-91ae-364da2661108",
"shortName": "CVE"
},
"references": [
{
"name": "https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-49q7-2jmh-92fp",
"tags": [
"x_refsource_CONFIRM",
"x_transferred"
],
"url": "https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-49q7-2jmh-92fp"
},
{
"name": "https://github.com/ggerganov/llama.cpp/commit/07283b1a90e1320aae4762c7e03c879043910252",
"tags": [
"x_refsource_MISC",
"x_transferred"
],
"url": "https://github.com/ggerganov/llama.cpp/commit/07283b1a90e1320aae4762c7e03c879043910252"
}
],
"title": "CVE Program Container"
}
],
"cna": {
"affected": [
{
"product": "llama.cpp",
"vendor": "ggerganov",
"versions": [
{
"status": "affected",
"version": "\u003c b3427"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "llama.cpp provides LLM inference in C/C++. Prior to b3427, llama.cpp contains a null pointer dereference in gguf_init_from_file. This vulnerability is fixed in b3427."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "LOW",
"baseScore": 5.4,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "NONE",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:L",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-476",
"description": "CWE-476: NULL Pointer Dereference",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-07-22T17:28:47.708Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-49q7-2jmh-92fp",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-49q7-2jmh-92fp"
},
{
"name": "https://github.com/ggerganov/llama.cpp/commit/07283b1a90e1320aae4762c7e03c879043910252",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/ggerganov/llama.cpp/commit/07283b1a90e1320aae4762c7e03c879043910252"
}
],
"source": {
"advisory": "GHSA-49q7-2jmh-92fp",
"discovery": "UNKNOWN"
},
"title": "llama.cpp null pointer dereference in gguf_init_from_file"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2024-41130",
"datePublished": "2024-07-22T17:28:47.708Z",
"dateReserved": "2024-07-15T15:53:28.324Z",
"dateUpdated": "2024-08-02T04:46:51.141Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2025-52566 (GCVE-0-2025-52566)
Vulnerability from cvelistv5
Published
2025-06-24 03:21
Modified
2025-06-24 21:49
Severity ?
VLAI Severity ?
EPSS score ?
CWE
Summary
llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp's tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.
References
| ▼ | URL | Tags |
|---|---|---|
| https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx | x_refsource_CONFIRM | |
| https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af | x_refsource_MISC |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2025-52566",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-06-24T21:49:17.452816Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2025-06-24T21:49:53.200Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "llama.cpp",
"vendor": "ggml-org",
"versions": [
{
"status": "affected",
"version": "\u003c b5721"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp\u0027s tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "HIGH",
"baseScore": 8.6,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-119",
"description": "CWE-119: Improper Restriction of Operations within the Bounds of a Memory Buffer",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-195",
"description": "CWE-195: Signed to Unsigned Conversion Error",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-06-24T03:21:19.009Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx"
},
{
"name": "https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af"
}
],
"source": {
"advisory": "GHSA-7rxv-5jhh-j6xx",
"discovery": "UNKNOWN"
},
"title": "llama.cpp tokenizer signed vs. unsigned heap overflow"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2025-52566",
"datePublished": "2025-06-24T03:21:19.009Z",
"dateReserved": "2025-06-18T03:55:52.036Z",
"dateUpdated": "2025-06-24T21:49:53.200Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2024-32878 (GCVE-0-2024-32878)
Vulnerability from cvelistv5
Published
2024-04-26 20:31
Modified
2024-08-02 02:20
Severity ?
VLAI Severity ?
EPSS score ?
CWE
- CWE-456 - Missing Initialization of a Variable
Summary
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.
References
| ▼ | URL | Tags |
|---|---|---|
| https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv | x_refsource_CONFIRM | |
| https://github.com/ggerganov/llama.cpp/releases/tag/b2749 | x_refsource_MISC |
{
"containers": {
"adp": [
{
"affected": [
{
"cpes": [
"cpe:2.3:a:ggerganov:llama.cpp:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unknown",
"product": "llama.cpp",
"vendor": "ggerganov",
"versions": [
{
"lessThanOrEqual": "b2715",
"status": "affected",
"version": "0",
"versionType": "custom"
}
]
}
],
"metrics": [
{
"other": {
"content": {
"id": "CVE-2024-32878",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-04-29T15:15:10.996975Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2024-07-03T14:57:34.597Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
},
{
"providerMetadata": {
"dateUpdated": "2024-08-02T02:20:35.603Z",
"orgId": "af854a3a-2127-422b-91ae-364da2661108",
"shortName": "CVE"
},
"references": [
{
"name": "https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv",
"tags": [
"x_refsource_CONFIRM",
"x_transferred"
],
"url": "https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv"
},
{
"name": "https://github.com/ggerganov/llama.cpp/releases/tag/b2749",
"tags": [
"x_refsource_MISC",
"x_transferred"
],
"url": "https://github.com/ggerganov/llama.cpp/releases/tag/b2749"
}
],
"title": "CVE Program Container"
}
],
"cna": {
"affected": [
{
"product": "llama.cpp",
"vendor": "ggerganov",
"versions": [
{
"status": "affected",
"version": "\u003c= b2715"
}
]
}
],
"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"
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "LOW",
"baseScore": 7.1,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:L",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-456",
"description": "CWE-456: Missing Initialization of a Variable",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-04-26T20:31:53.813Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv"
},
{
"name": "https://github.com/ggerganov/llama.cpp/releases/tag/b2749",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/ggerganov/llama.cpp/releases/tag/b2749"
}
],
"source": {
"advisory": "GHSA-p5mv-gjc5-mwqv",
"discovery": "UNKNOWN"
},
"title": " Use of Uninitialized Variable Vulnerability in llama.cpp"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2024-32878",
"datePublished": "2024-04-26T20:31:53.813Z",
"dateReserved": "2024-04-19T14:07:11.230Z",
"dateUpdated": "2024-08-02T02:20:35.603Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2025-49847 (GCVE-0-2025-49847)
Vulnerability from cvelistv5
Published
2025-06-17 20:04
Modified
2025-06-18 13:41
Severity ?
VLAI Severity ?
EPSS score ?
CWE
Summary
llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker‐supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp’s vocabulary‐loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length < (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662.
References
| ▼ | URL | Tags |
|---|---|---|
| https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqr | x_refsource_CONFIRM | |
| https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5 | x_refsource_MISC |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2025-49847",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-06-18T13:40:43.172535Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2025-06-18T13:41:11.407Z",
"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 b5662"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker\u2010supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp\u2019s vocabulary\u2010loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length \u003c (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-119",
"description": "CWE-119: Improper Restriction of Operations within the Bounds of a Memory Buffer",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-195",
"description": "CWE-195: Signed to Unsigned Conversion Error",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-06-17T20:04:40.893Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqr",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqr"
},
{
"name": "https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5"
}
],
"source": {
"advisory": "GHSA-8wwf-w4qm-gpqr",
"discovery": "UNKNOWN"
},
"title": "llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2025-49847",
"datePublished": "2025-06-17T20:04:40.893Z",
"dateReserved": "2025-06-11T14:33:57.800Z",
"dateUpdated": "2025-06-18T13:41:11.407Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
Vulnerability from fkie_nvd
Published
2025-06-24 04:15
Modified
2025-08-27 14:01
Severity ?
8.6 (High) - CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
8.8 (High) - CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
8.8 (High) - CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Summary
llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp's tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.
References
{
"configurations": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*",
"matchCriteriaId": "DC465FEB-FFD7-42D5-8D81-F416C28985BD",
"versionEndExcluding": "b5721",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp\u0027s tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721."
},
{
"lang": "es",
"value": "llama.cpp es una inferencia de varios modelos LLM en C/C++. Antes de la versi\u00f3n b5721, se produc\u00eda un desbordamiento de enteros con signo y sin signo en la implementaci\u00f3n del tokenizador de llama.cpp (llama_vocab::tokenize) (src/llama-vocab.cpp:3036), lo que provocaba un comportamiento no deseado al comparar el tama\u00f1o de copia de tokens. Esto permit\u00eda el desbordamiento del mont\u00f3n del motor de inferencia de llama.cpp con una entrada de texto cuidadosamente manipulada durante el proceso de tokenizaci\u00f3n. Este problema se ha corregido en la versi\u00f3n b5721."
}
],
"id": "CVE-2025-52566",
"lastModified": "2025-08-27T14:01:31.297",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "HIGH",
"baseScore": 8.6,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H",
"version": "3.1"
},
"exploitabilityScore": 1.8,
"impactScore": 6.0,
"source": "security-advisories@github.com",
"type": "Secondary"
},
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
},
"exploitabilityScore": 2.8,
"impactScore": 5.9,
"source": "nvd@nist.gov",
"type": "Primary"
}
]
},
"published": "2025-06-24T04:15:46.967",
"references": [
{
"source": "security-advisories@github.com",
"tags": [
"Patch"
],
"url": "https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af"
},
{
"source": "security-advisories@github.com",
"tags": [
"Exploit",
"Vendor Advisory"
],
"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx"
},
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"tags": [
"Exploit",
"Vendor Advisory"
],
"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx"
}
],
"sourceIdentifier": "security-advisories@github.com",
"vulnStatus": "Analyzed",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-119"
},
{
"lang": "en",
"value": "CWE-195"
}
],
"source": "security-advisories@github.com",
"type": "Secondary"
}
]
}
Vulnerability from fkie_nvd
Published
2024-07-22 18:15
Modified
2025-08-27 16:20
Severity ?
5.4 (Medium) - CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:L
6.5 (Medium) - CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H
6.5 (Medium) - CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H
Summary
llama.cpp provides LLM inference in C/C++. Prior to b3427, llama.cpp contains a null pointer dereference in gguf_init_from_file. This vulnerability is fixed in b3427.
References
{
"configurations": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*",
"matchCriteriaId": "D60FB0D9-E09B-48B8-9089-1B0C102F337F",
"versionEndExcluding": "b3427",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "llama.cpp provides LLM inference in C/C++. Prior to b3427, llama.cpp contains a null pointer dereference in gguf_init_from_file. This vulnerability is fixed in b3427."
},
{
"lang": "es",
"value": " llama.cpp proporciona inferencia LLM en C/C++. Antes de b3427, llama.cpp contiene una desreferencia de puntero nulo en gguf_init_from_file. Esta vulnerabilidad se soluciona en b3427."
}
],
"id": "CVE-2024-41130",
"lastModified": "2025-08-27T16:20:20.530",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "LOW",
"baseScore": 5.4,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "NONE",
"integrityImpact": "LOW",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:L",
"version": "3.1"
},
"exploitabilityScore": 2.8,
"impactScore": 2.5,
"source": "security-advisories@github.com",
"type": "Secondary"
},
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 6.5,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "NONE",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H",
"version": "3.1"
},
"exploitabilityScore": 2.8,
"impactScore": 3.6,
"source": "nvd@nist.gov",
"type": "Primary"
}
]
},
"published": "2024-07-22T18:15:04.013",
"references": [
{
"source": "security-advisories@github.com",
"tags": [
"Patch"
],
"url": "https://github.com/ggerganov/llama.cpp/commit/07283b1a90e1320aae4762c7e03c879043910252"
},
{
"source": "security-advisories@github.com",
"tags": [
"Third Party Advisory"
],
"url": "https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-49q7-2jmh-92fp"
},
{
"source": "af854a3a-2127-422b-91ae-364da2661108",
"tags": [
"Patch"
],
"url": "https://github.com/ggerganov/llama.cpp/commit/07283b1a90e1320aae4762c7e03c879043910252"
},
{
"source": "af854a3a-2127-422b-91ae-364da2661108",
"tags": [
"Third Party Advisory"
],
"url": "https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-49q7-2jmh-92fp"
}
],
"sourceIdentifier": "security-advisories@github.com",
"vulnStatus": "Analyzed",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-476"
}
],
"source": "security-advisories@github.com",
"type": "Secondary"
}
]
}
Vulnerability from fkie_nvd
Published
2025-06-17 20:15
Modified
2025-08-27 13:48
Severity ?
Summary
llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker‐supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp’s vocabulary‐loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length < (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662.
References
{
"configurations": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*",
"matchCriteriaId": "CD259F6A-4B43-4B07-83A5-544F900CD023",
"versionEndExcluding": "b5662",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker\u2010supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp\u2019s vocabulary\u2010loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length \u003c (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662."
},
{
"lang": "es",
"value": "llama.cpp es una inferencia de varios modelos LLM en C/C++. Antes de la versi\u00f3n b5662, un vocabulario de modelo GGUF proporcionado por un atacante pod\u00eda provocar un desbordamiento de b\u00fafer en el c\u00f3digo de carga de vocabulario de llama.cpp. Espec\u00edficamente, el asistente _try_copy en llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() convierte una longitud de token size_t muy grande en un int32_t, lo que provoca que se omita la comprobaci\u00f3n de longitud (si (length \u0026lt; (int32_t)size)). Como resultado, se sigue llamando a memcpy con ese tama\u00f1o excesivo, lo que permite que un modelo malicioso sobrescriba la memoria m\u00e1s all\u00e1 del b\u00fafer previsto. Esto puede provocar corrupci\u00f3n de memoria arbitraria y la posible ejecuci\u00f3n de c\u00f3digo. Este problema se ha corregido en la versi\u00f3n b5662."
}
],
"id": "CVE-2025-49847",
"lastModified": "2025-08-27T13:48:14.223",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
},
"exploitabilityScore": 2.8,
"impactScore": 5.9,
"source": "security-advisories@github.com",
"type": "Secondary"
}
]
},
"published": "2025-06-17T20:15:32.437",
"references": [
{
"source": "security-advisories@github.com",
"tags": [
"Patch"
],
"url": "https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5"
},
{
"source": "security-advisories@github.com",
"tags": [
"Mitigation",
"Vendor Advisory"
],
"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqr"
}
],
"sourceIdentifier": "security-advisories@github.com",
"vulnStatus": "Analyzed",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-119"
},
{
"lang": "en",
"value": "CWE-195"
}
],
"source": "security-advisories@github.com",
"type": "Primary"
}
]
}
Vulnerability from fkie_nvd
Published
2024-04-26 21:15
Modified
2025-09-02 18:30
Severity ?
7.1 (High) - CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:L
8.8 (High) - CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
8.8 (High) - CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Summary
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.
References
{
"configurations": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*",
"matchCriteriaId": "26E87746-7267-4255-B93E-3935A6A85278",
"versionEndExcluding": "b2740",
"versionStartIncluding": "b2715",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"cveTags": [],
"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."
}
],
"id": "CVE-2024-32878",
"lastModified": "2025-09-02T18:30:15.713",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "LOW",
"baseScore": 7.1,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:L",
"version": "3.1"
},
"exploitabilityScore": 1.6,
"impactScore": 5.5,
"source": "security-advisories@github.com",
"type": "Secondary"
},
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
},
"exploitabilityScore": 2.8,
"impactScore": 5.9,
"source": "nvd@nist.gov",
"type": "Primary"
}
]
},
"published": "2024-04-26T21:15:49.260",
"references": [
{
"source": "security-advisories@github.com",
"tags": [
"Release Notes"
],
"url": "https://github.com/ggerganov/llama.cpp/releases/tag/b2749"
},
{
"source": "security-advisories@github.com",
"tags": [
"Vendor Advisory"
],
"url": "https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv"
},
{
"source": "af854a3a-2127-422b-91ae-364da2661108",
"tags": [
"Release Notes"
],
"url": "https://github.com/ggerganov/llama.cpp/releases/tag/b2749"
},
{
"source": "af854a3a-2127-422b-91ae-364da2661108",
"tags": [
"Vendor Advisory"
],
"url": "https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-p5mv-gjc5-mwqv"
}
],
"sourceIdentifier": "security-advisories@github.com",
"vulnStatus": "Analyzed",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-456"
}
],
"source": "security-advisories@github.com",
"type": "Secondary"
}
]
}