CVE-2026-21869

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.

CVSS v3 8.8 HIGH

8.8^/10

CVSS v3 : HIGH

Vector :

Exploitability : 2.8 / Impact : 5.9

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction REQUIRED

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact HIGH

Scope UNCHANGED

References

Link	Resource
https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c	Exploit Vendor Advisory
https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c	Exploit Vendor Advisory

Configurations

Configuration 1 (hide)

cpe:2.3:a:ggml:llama.cpp:-:*:*:*:*:*:*:*

History

No history.

Information

Published : 2026-01-08 00:16

Updated : 2026-02-02 19:12

NVD link : CVE-2026-21869

Mitre link : CVE-2026-21869

CVE.ORG link : CVE-2026-21869

JSON object : View

Products Affected

ggml

llama.cpp

CWE

CWE-787

Out-of-bounds Write

{"id": "CVE-2026-21869", "cveTags": [], "metrics": {"cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"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"}, "impactScore": 5.9, "exploitabilityScore": 2.8}, {"type": "Primary", "source": "nvd@nist.gov", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 9.8, "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 5.9, "exploitabilityScore": 3.9}]}, "published": "2026-01-08T00:16:00.297", "references": [{"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c", "tags": ["Exploit", "Vendor Advisory"], "source": "security-advisories@github.com"}, {"url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c", "tags": ["Exploit", "Vendor Advisory"], "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-787"}]}], "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."}], "lastModified": "2026-02-02T19:12:36.020", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:ggml:llama.cpp:-:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "0A466917-A76C-4F63-B744-EC07FFB90CAF"}], "operator": "OR"}]}], "sourceIdentifier": "security-advisories@github.com"}