Search
Find a vulnerability
Search criteria
ⓘ
Use this form to refine search results.
Full-text search supports keyword queries with ranking and filtering.
You can combine vendor, product, and sources to narrow results.
Enable “Apply ordering” to sort by date instead of relevance.
10 vulnerabilities by ggml-org
CVE-2026-10298 (GCVE-0-2026-10298)
Vulnerability from cvelistv5 – Published: 2026-06-01 22:30 – Updated: 2026-06-02 15:45
VLAI
Title
ggml-org whisper.cpp ggml.c whisper_model_load null pointer dereference
Summary
A security flaw has been discovered in ggml-org whisper.cpp up to 1.8.2. This vulnerability affects the function whisper_model_load of the file ggml/src/ggml.c. The manipulation results in null pointer dereference. Attacking locally is a requirement. The exploit has been released to the public and may be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.
Severity
SSVC
Exploitation: poc
Automatable: no
Technical Impact: partial
CISA Coordinator (v2.0.3)
Assigner
References
6 references
| URL | Tags |
|---|---|
| https://vuldb.com/vuln/367591 | vdb-entrytechnical-description |
| https://vuldb.com/vuln/367591/cti | signaturepermissions-required |
| https://vuldb.com/cve/CVE-2026-10298 | third-party-advisory |
| https://vuldb.com/submit/826910 | third-party-advisory |
| https://github.com/ggml-org/whisper.cpp/issues/3807 | exploitissue-tracking |
| https://github.com/ggml-org/whisper.cpp/ | product |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| ggml-org | whisper.cpp |
Affected:
1.8.0
Affected: 1.8.1 Affected: 1.8.2 cpe:2.3:a:ggml-org:whisper.cpp:*:*:*:*:*:*:*:* |
Credits
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-10298",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-06-02T14:54:12.817409Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-06-02T15:45:34.998Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"cpes": [
"cpe:2.3:a:ggml-org:whisper.cpp:*:*:*:*:*:*:*:*"
],
"product": "whisper.cpp",
"vendor": "ggml-org",
"versions": [
{
"status": "affected",
"version": "1.8.0"
},
{
"status": "affected",
"version": "1.8.1"
},
{
"status": "affected",
"version": "1.8.2"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "reporter",
"value": "m00dy (VulDB User)"
},
{
"lang": "en",
"type": "coordinator",
"value": "VulDB CNA Team"
}
],
"descriptions": [
{
"lang": "en",
"value": "A security flaw has been discovered in ggml-org whisper.cpp up to 1.8.2. This vulnerability affects the function whisper_model_load of the file ggml/src/ggml.c. The manipulation results in null pointer dereference. Attacking locally is a requirement. The exploit has been released to the public and may be used for attacks. The project was informed of the problem early through an issue report but has not responded yet."
}
],
"metrics": [
{
"cvssV4_0": {
"baseScore": 4.8,
"baseSeverity": "MEDIUM",
"vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P",
"version": "4.0"
}
},
{
"cvssV3_1": {
"baseScore": 3.3,
"baseSeverity": "LOW",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L/E:P/RL:X/RC:R",
"version": "3.1"
}
},
{
"cvssV3_0": {
"baseScore": 3.3,
"baseSeverity": "LOW",
"vectorString": "CVSS:3.0/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L/E:P/RL:X/RC:R",
"version": "3.0"
}
},
{
"cvssV2_0": {
"baseScore": 1.7,
"vectorString": "AV:L/AC:L/Au:S/C:N/I:N/A:P/E:POC/RL:ND/RC:UR",
"version": "2.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-476",
"description": "NULL Pointer Dereference",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-404",
"description": "Denial of Service",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-06-01T22:30:10.751Z",
"orgId": "1af790b2-7ee1-4545-860a-a788eba489b5",
"shortName": "VulDB"
},
"references": [
{
"name": "VDB-367591 | ggml-org whisper.cpp ggml.c whisper_model_load null pointer dereference",
"tags": [
"vdb-entry",
"technical-description"
],
"url": "https://vuldb.com/vuln/367591"
},
{
"name": "VDB-367591 | CTI Indicators (IOB, IOC, IOA)",
"tags": [
"signature",
"permissions-required"
],
"url": "https://vuldb.com/vuln/367591/cti"
},
{
"name": "CVE-2026-10298 | CVE Analysis and Report",
"tags": [
"third-party-advisory"
],
"url": "https://vuldb.com/cve/CVE-2026-10298"
},
{
"name": "Submit #826910 | ggml-org whisper.cpp \u2264 1.8.2 (confirmed on HEAD as of 2026-05-12) NULL Pointer Dereference",
"tags": [
"third-party-advisory"
],
"url": "https://vuldb.com/submit/826910"
},
{
"tags": [
"exploit",
"issue-tracking"
],
"url": "https://github.com/ggml-org/whisper.cpp/issues/3807"
},
{
"tags": [
"product"
],
"url": "https://github.com/ggml-org/whisper.cpp/"
}
],
"timeline": [
{
"lang": "en",
"time": "2026-05-31T00:00:00.000Z",
"value": "Advisory disclosed"
},
{
"lang": "en",
"time": "2026-05-31T02:00:00.000Z",
"value": "VulDB entry created"
},
{
"lang": "en",
"time": "2026-05-31T20:09:51.000Z",
"value": "VulDB entry last update"
}
],
"title": "ggml-org whisper.cpp ggml.c whisper_model_load null pointer dereference"
}
},
"cveMetadata": {
"assignerOrgId": "1af790b2-7ee1-4545-860a-a788eba489b5",
"assignerShortName": "VulDB",
"cveId": "CVE-2026-10298",
"datePublished": "2026-06-01T22:30:10.751Z",
"dateReserved": "2026-05-31T18:04:48.553Z",
"dateUpdated": "2026-06-02T15:45:34.998Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-34159 (GCVE-0-2026-34159)
Vulnerability from cvelistv5 – Published: 2026-04-01 16:59 – Updated: 2026-04-02 03:56
VLAI
Title
llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend
Summary
llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages. Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been patched in version b8492.
Severity
9.8 (Critical)
SSVC
Exploitation: poc
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
- CWE-119 - Improper Restriction of Operations within the Bounds of a Memory Buffer
Assigner
References
3 references
| URL | Tags |
|---|---|
| https://github.com/ggml-org/llama.cpp/security/ad… | x_refsource_CONFIRM |
| https://github.com/ggml-org/llama.cpp/pull/20908 | x_refsource_MISC |
| https://github.com/ggml-org/llama.cpp/commit/39bf… | x_refsource_MISC |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-34159",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-04-01T00:00:00+00:00",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-04-02T03:56:11.820Z",
"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 b8492"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend\u0027s deserialize_tensor() skips all bounds validation when a tensor\u0027s buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages. Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been patched in version b8492."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.8,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/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"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-04-01T16:59:59.967Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw"
},
{
"name": "https://github.com/ggml-org/llama.cpp/pull/20908",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/ggml-org/llama.cpp/pull/20908"
},
{
"name": "https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042"
}
],
"source": {
"advisory": "GHSA-j8rj-fmpv-wcxw",
"discovery": "UNKNOWN"
},
"title": "llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-34159",
"datePublished": "2026-04-01T16:59:59.967Z",
"dateReserved": "2026-03-25T20:12:04.197Z",
"dateUpdated": "2026-04-02T03:56:11.820Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
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)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
Assigner
References
2 references
| URL | Tags |
|---|---|
| https://github.com/ggml-org/llama.cpp/security/ad… | x_refsource_CONFIRM |
| https://github.com/ggml-org/llama.cpp/releases/ta… | x_refsource_MISC |
{
"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"
}
CVE-2026-27940 (GCVE-0-2026-27940)
Vulnerability from cvelistv5 – Published: 2026-03-12 16:39 – Updated: 2026-03-14 03:55
VLAI
Title
llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 Fix
Summary
llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the buffer boundary. This is a bypass of a similar bug in the same file - CVE-2025-53630, but the fix overlooked some areas. This vulnerability is fixed in b8146.
Severity
7.8 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
Assigner
References
1 reference
| URL | Tags |
|---|---|
| https://github.com/ggml-org/llama.cpp/security/ad… | x_refsource_CONFIRM |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-27940",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-03-12T00:00:00+00:00",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-03-14T03:55:24.463Z",
"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 b8146"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the buffer boundary. This is a bypass of a similar bug in the same file - CVE-2025-53630, but the fix overlooked some areas. This vulnerability is fixed in b8146."
}
],
"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": "2026-03-12T16:39:37.463Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-3p4r-fq3f-q74v",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-3p4r-fq3f-q74v"
}
],
"source": {
"advisory": "GHSA-3p4r-fq3f-q74v",
"discovery": "UNKNOWN"
},
"title": "llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation \u2014 Bypass of CVE-2025-53630 Fix"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-27940",
"datePublished": "2026-03-12T16:39:37.463Z",
"dateReserved": "2026-02-25T03:11:36.689Z",
"dateUpdated": "2026-03-14T03:55:24.463Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-2069 (GCVE-0-2026-2069)
Vulnerability from cvelistv5 – Published: 2026-02-06 22:02 – Updated: 2026-02-23 09:28
VLAI
Title
ggml-org llama.cpp GBNF Grammar llama-grammar.cpp llama_grammar_advance_stack stack-based overflow
Summary
A flaw has been found in ggml-org llama.cpp up to 55abc39. Impacted is the function llama_grammar_advance_stack of the file llama.cpp/src/llama-grammar.cpp of the component GBNF Grammar Handler. This manipulation causes stack-based buffer overflow. The attack needs to be launched locally. The exploit has been published and may be used. Patch name: 18993. To fix this issue, it is recommended to deploy a patch.
Severity
SSVC
Exploitation: poc
Automatable: no
Technical Impact: partial
CISA Coordinator (v2.0.3)
Assigner
References
8 references
| URL | Tags |
|---|---|
| https://vuldb.com/?id.344636 | vdb-entrytechnical-description |
| https://vuldb.com/?ctiid.344636 | signaturepermissions-required |
| https://vuldb.com/?submit.745263 | third-party-advisory |
| https://github.com/ggml-org/llama.cpp/issues/18988 | issue-tracking |
| https://github.com/ggml-org/llama.cpp/issues/1898… | issue-tracking |
| https://github.com/user-attachments/files/2476110… | exploit |
| https://github.com/ggml-org/llama.cpp/pull/18993 | issue-trackingpatch |
| https://github.com/ggml-org/llama.cpp/ | product |
Credits
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-2069",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-02-10T15:18:13.164026Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-02-10T15:18:27.688Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"modules": [
"GBNF Grammar Handler"
],
"product": "llama.cpp",
"vendor": "ggml-org",
"versions": [
{
"status": "affected",
"version": "55abc39"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "reporter",
"value": "TYGLS (VulDB User)"
}
],
"descriptions": [
{
"lang": "en",
"value": "A flaw has been found in ggml-org llama.cpp up to 55abc39. Impacted is the function llama_grammar_advance_stack of the file llama.cpp/src/llama-grammar.cpp of the component GBNF Grammar Handler. This manipulation causes stack-based buffer overflow. The attack needs to be launched locally. The exploit has been published and may be used. Patch name: 18993. To fix this issue, it is recommended to deploy a patch."
}
],
"metrics": [
{
"cvssV4_0": {
"baseScore": 4.8,
"baseSeverity": "MEDIUM",
"vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P",
"version": "4.0"
}
},
{
"cvssV3_1": {
"baseScore": 3.3,
"baseSeverity": "LOW",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L/E:P/RL:O/RC:C",
"version": "3.1"
}
},
{
"cvssV3_0": {
"baseScore": 3.3,
"baseSeverity": "LOW",
"vectorString": "CVSS:3.0/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L/E:P/RL:O/RC:C",
"version": "3.0"
}
},
{
"cvssV2_0": {
"baseScore": 1.7,
"vectorString": "AV:L/AC:L/Au:S/C:N/I:N/A:P/E:POC/RL:OF/RC:C",
"version": "2.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-121",
"description": "Stack-based Buffer Overflow",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-119",
"description": "Memory Corruption",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-02-23T09:28:33.822Z",
"orgId": "1af790b2-7ee1-4545-860a-a788eba489b5",
"shortName": "VulDB"
},
"references": [
{
"name": "VDB-344636 | ggml-org llama.cpp GBNF Grammar llama-grammar.cpp llama_grammar_advance_stack stack-based overflow",
"tags": [
"vdb-entry",
"technical-description"
],
"url": "https://vuldb.com/?id.344636"
},
{
"name": "VDB-344636 | CTI Indicators (IOB, IOC, IOA)",
"tags": [
"signature",
"permissions-required"
],
"url": "https://vuldb.com/?ctiid.344636"
},
{
"name": "Submit #745263 | llama.cpp commit 55abc39 Stack-based Buffer Overflow",
"tags": [
"third-party-advisory"
],
"url": "https://vuldb.com/?submit.745263"
},
{
"tags": [
"issue-tracking"
],
"url": "https://github.com/ggml-org/llama.cpp/issues/18988"
},
{
"tags": [
"issue-tracking"
],
"url": "https://github.com/ggml-org/llama.cpp/issues/18988#event-4426704865"
},
{
"tags": [
"exploit"
],
"url": "https://github.com/user-attachments/files/24761101/poc.zip"
},
{
"tags": [
"issue-tracking",
"patch"
],
"url": "https://github.com/ggml-org/llama.cpp/pull/18993"
},
{
"tags": [
"product"
],
"url": "https://github.com/ggml-org/llama.cpp/"
}
],
"timeline": [
{
"lang": "en",
"time": "2026-02-06T00:00:00.000Z",
"value": "Advisory disclosed"
},
{
"lang": "en",
"time": "2026-02-06T01:00:00.000Z",
"value": "VulDB entry created"
},
{
"lang": "en",
"time": "2026-02-10T05:46:24.000Z",
"value": "VulDB entry last update"
}
],
"title": "ggml-org llama.cpp GBNF Grammar llama-grammar.cpp llama_grammar_advance_stack stack-based overflow"
}
},
"cveMetadata": {
"assignerOrgId": "1af790b2-7ee1-4545-860a-a788eba489b5",
"assignerShortName": "VulDB",
"cveId": "CVE-2026-2069",
"datePublished": "2026-02-06T22:02:08.933Z",
"dateReserved": "2026-02-06T07:41:07.150Z",
"dateUpdated": "2026-02-23T09:28:33.822Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-21869 (GCVE-0-2026-21869)
Vulnerability from cvelistv5 – Published: 2026-01-07 23:37 – Updated: 2026-01-08 19:15
VLAI
Title
llama.cpp has Out-of-bounds Write in llama-server
Summary
llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the n_discard parameter is parsed directly from JSON input in the llama.cpp server's completion endpoints without validation to ensure it's non-negative. When a negative value is supplied and the context fills up, llama_memory_seq_rm/add receives a reversed range and negative offset, causing out-of-bounds memory writes in the token evaluation loop. This deterministic memory corruption can crash the process or enable remote code execution (RCE). There is no fix at the time of publication.
Severity
8.8 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
- CWE-787 - Out-of-bounds Write
Assigner
References
1 reference
| URL | Tags |
|---|---|
| https://github.com/ggml-org/llama.cpp/security/ad… | x_refsource_CONFIRM |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-21869",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-01-08T19:15:25.248439Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-01-08T19:15:28.709Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "llama.cpp",
"vendor": "ggml-org",
"versions": [
{
"status": "affected",
"version": "\u003c= 55d4206c8"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "llama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the n_discard parameter is parsed directly from JSON input in the llama.cpp server\u0027s completion endpoints without validation to ensure it\u0027s non-negative. When a negative value is supplied and the context fills up, llama_memory_seq_rm/add receives a reversed range and negative offset, causing out-of-bounds memory writes in the token evaluation loop. This deterministic memory corruption can crash the process or enable remote code execution (RCE). There is no fix at the time of publication."
}
],
"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-787",
"description": "CWE-787: Out-of-bounds Write",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-01-07T23:37:59.886Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c"
}
],
"source": {
"advisory": "GHSA-8947-pfff-2f3c",
"discovery": "UNKNOWN"
},
"title": "llama.cpp has Out-of-bounds Write in llama-server"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-21869",
"datePublished": "2026-01-07T23:37:59.886Z",
"dateReserved": "2026-01-05T16:44:16.368Z",
"dateUpdated": "2026-01-08T19:15:28.709Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2025-14569 (GCVE-0-2025-14569)
Vulnerability from cvelistv5 – Published: 2025-12-12 18:02 – Updated: 2025-12-12 19:22
VLAI
Title
ggml-org whisper.cpp common-whisper.cpp read_audio_data use after free
Summary
A vulnerability was detected in ggml-org whisper.cpp up to 1.8.2. Affected is the function read_audio_data of the file /whisper.cpp/examples/common-whisper.cpp. The manipulation results in use after free. The attack requires a local approach. The exploit is now public and may be used. The project was informed of the problem early through an issue report but has not responded yet.
Severity
SSVC
Exploitation: none
Automatable: no
Technical Impact: partial
CISA Coordinator (v2.0.3)
Assigner
References
5 references
| URL | Tags |
|---|---|
| https://vuldb.com/?id.336193 | vdb-entrytechnical-description |
| https://vuldb.com/?ctiid.336193 | signaturepermissions-required |
| https://vuldb.com/?submit.703886 | third-party-advisory |
| https://github.com/ggml-org/whisper.cpp/issues/3501 | issue-tracking |
| https://github.com/oneafter/InvalidFree/blob/main/repro | exploit |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| ggml-org | whisper.cpp |
Affected:
1.8.0
Affected: 1.8.1 Affected: 1.8.2 |
Credits
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2025-14569",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-12-12T19:22:05.953080Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2025-12-12T19:22:15.061Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "whisper.cpp",
"vendor": "ggml-org",
"versions": [
{
"status": "affected",
"version": "1.8.0"
},
{
"status": "affected",
"version": "1.8.1"
},
{
"status": "affected",
"version": "1.8.2"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "repro"
},
{
"lang": "en",
"type": "reporter",
"value": "Oneafter (VulDB User)"
}
],
"descriptions": [
{
"lang": "en",
"value": "A vulnerability was detected in ggml-org whisper.cpp up to 1.8.2. Affected is the function read_audio_data of the file /whisper.cpp/examples/common-whisper.cpp. The manipulation results in use after free. The attack requires a local approach. The exploit is now public and may be used. The project was informed of the problem early through an issue report but has not responded yet."
}
],
"metrics": [
{
"cvssV4_0": {
"baseScore": 4.8,
"baseSeverity": "MEDIUM",
"vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P",
"version": "4.0"
}
},
{
"cvssV3_1": {
"baseScore": 5.3,
"baseSeverity": "MEDIUM",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R",
"version": "3.1"
}
},
{
"cvssV3_0": {
"baseScore": 5.3,
"baseSeverity": "MEDIUM",
"vectorString": "CVSS:3.0/AV:L/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R",
"version": "3.0"
}
},
{
"cvssV2_0": {
"baseScore": 4.3,
"vectorString": "AV:L/AC:L/Au:S/C:P/I:P/A:P/E:POC/RL:ND/RC:UR",
"version": "2.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-416",
"description": "Use After Free",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-119",
"description": "Memory Corruption",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-12-12T18:02:09.274Z",
"orgId": "1af790b2-7ee1-4545-860a-a788eba489b5",
"shortName": "VulDB"
},
"references": [
{
"name": "VDB-336193 | ggml-org whisper.cpp common-whisper.cpp read_audio_data use after free",
"tags": [
"vdb-entry",
"technical-description"
],
"url": "https://vuldb.com/?id.336193"
},
{
"name": "VDB-336193 | CTI Indicators (IOB, IOC, IOA)",
"tags": [
"signature",
"permissions-required"
],
"url": "https://vuldb.com/?ctiid.336193"
},
{
"name": "Submit #703886 | ggerganov whisper.cpp v1.8.2 Free of Memory not on the Heap",
"tags": [
"third-party-advisory"
],
"url": "https://vuldb.com/?submit.703886"
},
{
"tags": [
"issue-tracking"
],
"url": "https://github.com/ggml-org/whisper.cpp/issues/3501"
},
{
"tags": [
"exploit"
],
"url": "https://github.com/oneafter/InvalidFree/blob/main/repro"
}
],
"timeline": [
{
"lang": "en",
"time": "2025-12-12T00:00:00.000Z",
"value": "Advisory disclosed"
},
{
"lang": "en",
"time": "2025-12-12T01:00:00.000Z",
"value": "VulDB entry created"
},
{
"lang": "en",
"time": "2025-12-12T12:32:21.000Z",
"value": "VulDB entry last update"
}
],
"title": "ggml-org whisper.cpp common-whisper.cpp read_audio_data use after free"
}
},
"cveMetadata": {
"assignerOrgId": "1af790b2-7ee1-4545-860a-a788eba489b5",
"assignerShortName": "VulDB",
"cveId": "CVE-2025-14569",
"datePublished": "2025-12-12T18:02:09.274Z",
"dateReserved": "2025-12-12T11:27:00.916Z",
"dateUpdated": "2025-12-12T19:22:15.061Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2025-53630 (GCVE-0-2025-53630)
Vulnerability from cvelistv5 – Published: 2025-07-10 19:32 – Updated: 2025-07-10 20:31
VLAI
Title
Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in gguf
Summary
llama.cpp is an inference of several LLM models in C/C++. Integer Overflow in the gguf_init_from_file_impl function in ggml/src/gguf.cpp can lead to Heap Out-of-Bounds Read/Write. This vulnerability is fixed in commit 26a48ad699d50b6268900062661bd22f3e792579.
Severity
SSVC
Exploitation: poc
Automatable: no
Technical Impact: partial
CISA Coordinator (v2.0.3)
Assigner
References
2 references
| URL | Tags |
|---|---|
| https://github.com/ggml-org/llama.cpp/security/ad… | x_refsource_CONFIRM |
| https://github.com/ggml-org/llama.cpp/commit/26a4… | x_refsource_MISC |
Impacted products
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2025-53630",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2025-07-10T20:30:57.116005Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2025-07-10T20:31:07.240Z",
"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 26a48ad699d50b6268900062661bd22f3e792579"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "llama.cpp is an inference of several LLM models in C/C++. Integer Overflow in the gguf_init_from_file_impl function in ggml/src/gguf.cpp can lead to Heap Out-of-Bounds Read/Write. This vulnerability is fixed in commit 26a48ad699d50b6268900062661bd22f3e792579."
}
],
"metrics": [
{
"cvssV4_0": {
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.9,
"baseSeverity": "HIGH",
"privilegesRequired": "NONE",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:P",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-122",
"description": "CWE-122: Heap-based Buffer Overflow",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-680",
"description": "CWE-680: Integer Overflow to Buffer Overflow",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2025-07-10T19:32:45.296Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-vgg9-87g3-85w8",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-vgg9-87g3-85w8"
},
{
"name": "https://github.com/ggml-org/llama.cpp/commit/26a48ad699d50b6268900062661bd22f3e792579",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/ggml-org/llama.cpp/commit/26a48ad699d50b6268900062661bd22f3e792579"
}
],
"source": {
"advisory": "GHSA-vgg9-87g3-85w8",
"discovery": "UNKNOWN"
},
"title": "Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in gguf"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2025-53630",
"datePublished": "2025-07-10T19:32:45.296Z",
"dateReserved": "2025-07-07T14:20:38.389Z",
"dateUpdated": "2025-07-10T20:31:07.240Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
CVE-2025-52566 (GCVE-0-2025-52566)
Vulnerability from cvelistv5 – Published: 2025-06-24 03:21 – Updated: 2025-06-24 21:49
VLAI
Title
llama.cpp tokenizer signed vs. unsigned heap overflow
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.
Severity
8.6 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
Assigner
References
2 references
| URL | Tags |
|---|---|
| https://github.com/ggml-org/llama.cpp/security/ad… | x_refsource_CONFIRM |
| https://github.com/ggml-org/llama.cpp/commit/dd6e… | 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-2025-49847 (GCVE-0-2025-49847)
Vulnerability from cvelistv5 – Published: 2025-06-17 20:04 – Updated: 2025-06-18 13:41
VLAI
Title
llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model
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.
Severity
8.8 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
Assigner
References
2 references
| URL | Tags |
|---|---|
| https://github.com/ggml-org/llama.cpp/security/ad… | x_refsource_CONFIRM |
| https://github.com/ggml-org/llama.cpp/commit/3cfb… | 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"
}