CVE-2026-21869

{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-21869", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2026-01-05T16:44:16.368Z", "datePublished": "2026-01-07T23:37:59.886Z", "dateUpdated": "2026-01-08T19:15:28.709Z"}, "containers": {"cna": {"title": "llama.cpp has Out-of-bounds Write in llama-server", "problemTypes": [{"descriptions": [{"cweId": "CWE-787", "lang": "en", "description": "CWE-787: Out-of-bounds Write", "type": "CWE"}]}], "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"}}], "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"}], "affected": [{"vendor": "ggml-org", "product": "llama.cpp", "versions": [{"version": "<= 55d4206c8", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-01-07T23:37:59.886Z"}, "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'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."}], "source": {"advisory": "GHSA-8947-pfff-2f3c", "discovery": "UNKNOWN"}}, "adp": [{"references": [{"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c", "tags": ["exploit"]}], "metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2026-01-08T19:15:25.248439Z", "id": "CVE-2026-21869", "options": [{"Exploitation": "poc"}, {"Automatable": "no"}, {"Technical Impact": "total"}], "role": "CISA Coordinator", "version": "2.0.3"}}}], "title": "CISA ADP Vulnrichment", "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-01-08T19:15:28.709Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2026-21869", "role": "CISA Coordinator", "options": [{"Exploitation": "poc"}, {"Automatable": "no"}, {"Technical Impact": "total"}], "version": "2.0.3", "timestamp": "2026-01-08T19:15:25.248439Z"}}}], "references": [{"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c", "tags": ["exploit"]}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-01-08T19:15:19.593Z"}}], "cna": {"title": "llama.cpp has Out-of-bounds Write in llama-server", "source": {"advisory": "GHSA-8947-pfff-2f3c", "discovery": "UNKNOWN"}, "metrics": [{"cvssV3_1": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 8.8, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/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": "<= 55d4206c8"}]}], "references": [{"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c", "name": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c", "tags": ["x_refsource_CONFIRM"]}], "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'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."}], "problemTypes": [{"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-787", "description": "CWE-787: Out-of-bounds Write"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2026-01-07T23:37:59.886Z"}}}, "cveMetadata": {"cveId": "CVE-2026-21869", "state": "PUBLISHED", "dateUpdated": "2026-01-08T19:15:28.709Z", "dateReserved": "2026-01-05T16:44:16.368Z", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "datePublished": "2026-01-07T23:37:59.886Z", "assignerShortName": "GitHub_M"}, "dataVersion": "5.2"}

{"affected": [{"affectedData": [{"product": "llama.cpp", "vendor": "ggml-org", "versions": [{"status": "affected", "version": "<= 55d4206c8"}]}], "source": "security-advisories@github.com"}], "configurations": [{"nodes": [{"cpeMatch": [{"criteria": "cpe:2.3:a:ggml:llama.cpp:-:*:*:*:*:*:*:*", "matchCriteriaId": "0A466917-A76C-4F63-B744-EC07FFB90CAF", "vulnerable": true}], "negate": false, "operator": "OR"}]}], "cveTags": [], "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'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."}, {"lang": "es", "value": "llama.cpp es una inferencia de varios modelos LLM en C/C++. En los commits 55d4206c8 y anteriores, el par\u00e1metro n_discard se analiza directamente de la entrada JSON en los puntos finales de completado del servidor de llama.cpp sin validaci\u00f3n para asegurar que no sea negativo. Cuando se suministra un valor negativo y el contexto se llena, llama_memory_seq_rm/add recibe un rango invertido y un desplazamiento negativo, causando escrituras de memoria fuera de l\u00edmites en el bucle de evaluaci\u00f3n de tokens. Esta corrupci\u00f3n de memoria determinista puede bloquear el proceso o permitir la ejecuci\u00f3n remota de c\u00f3digo (RCE). No hay una soluci\u00f3n en el momento de la publicaci\u00f3n."}], "id": "CVE-2026-21869", "lastModified": "2026-06-17T10:19:03.657", "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"}, {"cvssData": {"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"}, "exploitabilityScore": 3.9, "impactScore": 5.9, "source": "nvd@nist.gov", "type": "Primary"}], "ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-21869", "options": [{"exploitation": "poc"}, {"automatable": "no"}, {"technicalImpact": "total"}], "role": "CISA Coordinator", "timestamp": "2026-01-08T19:15:25.248439Z", "version": "2.0.3"}}]}, "published": "2026-01-08T00:16:00.297", "references": [{"source": "security-advisories@github.com", "tags": ["Exploit", "Vendor Advisory"], "url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c"}, {"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "tags": ["Exploit", "Vendor Advisory"], "url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c"}], "sourceIdentifier": "security-advisories@github.com", "vulnStatus": "Analyzed", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-787"}], "source": "security-advisories@github.com", "type": "Secondary"}]}

{"bugzilla": {"description": "llama.cpp: llama.cpp: Remote code execution via invalid n_discard parameter in server endpoints", "id": "2427743", "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2427743"}, "csaw": false, "cvss3": {"cvss3_base_score": "8.1", "cvss3_scoring_vector": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H", "status": "draft"}, "cwe": "CWE-787", "details": ["A flaw was found in llama.cpp. A remote attacker can exploit an input validation vulnerability in the server's completion endpoints. By supplying a negative value for the `n_discard` parameter in JSON input, an attacker can cause out-of-bounds memory writes. This can lead to a process crash or enable remote code execution (RCE), allowing the attacker to run arbitrary code on the affected system."], "name": "CVE-2026-21869", "public_date": "2026-01-07T23:37:59Z", "references": ["https://www.cve.org/CVERecord?id=CVE-2026-21869\nhttps://nvd.nist.gov/vuln/detail/CVE-2026-21869\nhttps://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c"], "statement": "This vulnerability is rated Important as it allows remote code execution in the llama.cpp server. An unauthenticated remote attacker can trigger out-of-bounds memory writes by providing a negative `n_discard` parameter in JSON input to the server's completion endpoints, leading to a crash or arbitrary code execution. This could impact deployments where the llama.cpp server is exposed to untrusted networks.", "threat_severity": "Important"}

{"analysis": {"en": {"generated_at": "2026-04-18T07:51:18.405102+00:00", "value": {"mitigation_remediation": ["Upgrade to a revised llama.cpp release that validates the n_discard parameter or applies the fix described in the advisory.", "Harden network exposure by limiting access to the llama.cpp server behind a firewall or by using IP whitelisting.", "Implement server\u2011side input validation to reject negative n_discard values before processing requests."], "summary": {"action": "Assess Impact", "impact": "Remote code execution"}, "threat_synthesis": {"affected_systems": "The vulnerability affects the ggml-org llama.cpp implementation, specifically versions associated with commit 55d4206c8 and earlier. No version list is provided, so any release prior to a forthcoming fix is potentially exposed. The affected component is the llama.cpp server\u2019s completion endpoints receiving JSON input.", "description_and_impact": "An out\u2011of\u2011bounds memory write is triggered when the llama.cpp server parses the n_discard parameter from JSON input without verifying that it is non\u2011negative. Supplying a negative value causes the memory removal routine to use a reversed range and negative offset, corrupting memory during the token evaluation loop. This deterministic corruption can crash the process or, in a remote context, enable code execution.", "risk_and_exploitability": "The CVSS score of 8.8 indicates a high severity, but the EPSS score of less than 1% suggests a low exploitation probability at this time. The vulnerability is not listed in the KEV catalog. A remote attacker can trigger the flaw by sending a crafted JSON request to the server\u2019s completion endpoint with a negative n_discard value. Without a patch, mitigating such an attack would require input validation or network restriction."}}}}, "created": "2026-01-08T09:47:51.233367+00:00", "updated": "2026-04-18T08:00:05.790682+00:00", "vendors": ["ggml", "ggml$PRODUCT$llama.cpp"]}