Vulnerability-Lookup

FKIE_CVE-2026-21869

Vulnerability from fkie_nvd - Published: 2026-01-08 00:16 - Updated: 2026-06-17 10:19

Severity

8.8 (High) - CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
9.8 (Critical) - CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

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.

References

	URL	Tags
	security-advisories@github.com	https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c	Exploit, Vendor Advisory
	134c704f-9b21-4f2e-91b3-4a467353bcc0	https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c	Exploit, Vendor Advisory

Impacted products

	Vendor	Product	Version
	ggml	llama.cpp	-

JSON

To clipboard

{
  "affected": [
    {
      "affectedData": [
        {
          "product": "llama.cpp",
          "vendor": "ggml-org",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c= 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\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."
    },
    {
      "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"
    }
  ]
}

CVE-2026-21869 (GCVE-0-2026-21869)

Vulnerability from cvelistv5 – Published: 2026-01-07 23:37 – Updated: 2026-01-08 19:15

Title

llama.cpp has Out-of-bounds Write in llama-server

Summary

Severity

8.8 (High)


                        
                          CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

SSVC

Exploitation: poc Automatable: no Technical Impact: total

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-01-08 19:15 UTC

CWE

CWE-787 - Out-of-bounds Write

Assigner

GitHub_M CNA under the mitre root

CNA scorecard C 72/100 over 7814 records in the last 180 days details

References

1 reference

URL	Tags
https://github.com/ggml-org/llama.cpp/security/ad…	x_refsource_CONFIRM

Impacted products

1 product

Vendor	Product	Version
ggml-org	llama.cpp	Affected: <= 55d4206c8

Show details on NVD website

JSON

To clipboard

{
  "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"
}

Sightings

Author	Source	Type	Date	Other

Nomenclature

Seen: The vulnerability was mentioned, discussed, or observed by the user.
Confirmed: The vulnerability has been validated from an analyst's perspective.
Published Proof of Concept: A public proof of concept is available for this vulnerability.
Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
Not confirmed: The user expressed doubt about the validity of the vulnerability.
Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.

Vulnerability timeline

Sightings and recorded dates, grouped by day · UTC

Order JSON

How durations are calculated

Following the VTEM framework (Black Hat USA 2015), time to patch starts when the vendor or a coordinator was informed, total time to patch at discovery, and disclosure to patch at public disclosure; vendor response time runs from the report to its acknowledgement. Time to exploit and time unpatched start at the earliest discovery or report, falling back to public disclosure. Unpatched time ends at the first recorded patch, or the calculation time when no patch is recorded. Exploitation to patch shows the interval between those two events; a published proof of concept is a public exploit, not exploitation.

Each result shows its source dates. A negative interval means the end event came first; when date-only inputs leave the order open, the result says so. Date-only inputs are approximate. The earliest evidence wins: KEV report dates and sightings are labelled as such. Records describing another vulnerability are listed but never calculated from, and a PoC alone does not establish exploitation. Missing patch evidence does not prove that no patch exists. Filters below change the event list only.

Publication & reservation Sightings KEV catalogs Other timestamps

Loading timeline…

The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.

Action not permitted