Vulnerability-Lookup

GHSA-3R8C-J789-2864

Vulnerability from github – Published: 2026-10-27 03:32 – Updated: 2026-10-27 03:32

Details

llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llm_tokenizer_plamo2::build that allows attackers to corrupt heap memory via crafted GGUF models. Attackers can supply BYTE-typed token text like <0x-1> whose negative parsed value writes token ids before the bytes_ buffer during model loading, causing crashes or potential code execution.

Severity

7.8 (High)


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

8.5 (High)


                  
                    CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2026-116816"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-129"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-10-27T01:19:06Z",
    "severity": "HIGH"
  },
  "details": "llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llm_tokenizer_plamo2::build that allows attackers to corrupt heap memory via crafted GGUF models. Attackers can supply BYTE-typed token text like \u003c0x-1\u003e whose negative parsed value writes token ids before the bytes_ buffer during model loading, causing crashes or potential code execution.",
  "id": "GHSA-3r8c-j789-2864",
  "modified": "2026-10-27T03:32:10Z",
  "published": "2026-10-27T03:32:10Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-116816"
    },
    {
      "type": "WEB",
      "url": "https://github.com/ggml-org/llama.cpp/pull/25969"
    },
    {
      "type": "WEB",
      "url": "https://github.com/ggml-org/llama.cpp/pull/26511"
    },
    {
      "type": "WEB",
      "url": "https://github.com/ggml-org/llama.cpp/commit/cf06ad7dfe79e7bf2934150d4fefe1ce8db05490"
    },
    {
      "type": "WEB",
      "url": "https://github.com/ggml-org/llama.cpp/blob/b10259/src/llama-vocab.cpp#L1376-L1377"
    },
    {
      "type": "WEB",
      "url": "https://github.com/ggml-org/llama.cpp/releases/tag/b10261"
    },
    {
      "type": "WEB",
      "url": "https://www.vulncheck.com/advisories/llama-cpp-b5899-before-b10261-heap-out-of-bounds-write-via-plamo2-tokenizer"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
      "type": "CVSS_V4"
    }
  ]
}

CVE-2026-116816 (GCVE-0-2026-116816)

Vulnerability from cvelistv5 – Published: 2026-10-27 00:33 – Updated: 2026-10-27 00:33

Title

llama.cpp b5899 before b10261 Heap Out-of-Bounds Write via plamo2 Tokenizer

Summary

Severity

8.5 (High)


                        
                          CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

7.8 (High)


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

CWE

CWE-129 - Improper Validation of Array Index

Assigner

VulnCheck CNA under the mitre root

CNA scorecard B 84/100 over 6903 records in the last 180 days details

References

6 references

URL	Tags
https://github.com/ggml-org/llama.cpp/pull/25969	issue-trackingpatch
https://github.com/ggml-org/llama.cpp/pull/26511	patchissue-tracking
https://github.com/ggml-org/llama.cpp/commit/cf06…	patch
https://github.com/ggml-org/llama.cpp/blob/b10259…	technical-description
https://github.com/ggml-org/llama.cpp/releases/ta…	release-notes
https://www.vulncheck.com/advisories/llama-cpp-b5…	third-party-advisory

Impacted products

1 product

Vendor	Product	Version
ggml-org	llama.cpp	Affected: b5899 , < b10261 (custom) cpe:2.3:a:ggml:llama.cpp::::::::

Date Public

2026-07-21 00:00

Credits

Pedro Cruz (g4nkd) Jeongwoo Lee CISC

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "packageURL": "pkg:github/ggml-org/llama.cpp",
          "product": "llama.cpp",
          "vendor": "ggml-org",
          "versions": [
            {
              "lessThan": "b10261",
              "status": "affected",
              "version": "b5899",
              "versionType": "custom"
            }
          ]
        }
      ],
      "cpeApplicability": [
        {
          "nodes": [
            {
              "cpeMatch": [
                {
                  "criteria": "cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*",
                  "versionEndExcluding": "b10261",
                  "versionStartIncluding": "b5899",
                  "vulnerable": true
                }
              ],
              "negate": false,
              "operator": "OR"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "Pedro Cruz (g4nkd)"
        },
        {
          "lang": "en",
          "type": "reporter",
          "value": "Jeongwoo Lee"
        },
        {
          "lang": "en",
          "type": "remediation developer",
          "value": "CISC"
        }
      ],
      "datePublic": "2026-07-21T00:00:00.000Z",
      "descriptions": [
        {
          "lang": "en",
          "value": "llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llm_tokenizer_plamo2::build that allows attackers to corrupt heap memory via crafted GGUF models. Attackers can supply BYTE-typed token text like \u003c0x-1\u003e whose negative parsed value writes token ids before the bytes_ buffer during model loading, causing crashes or potential code execution."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "LOCAL",
            "baseScore": 8.5,
            "baseSeverity": "HIGH",
            "privilegesRequired": "NONE",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "PASSIVE",
            "vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "HIGH"
          },
          "format": "CVSS"
        },
        {
          "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"
          },
          "format": "CVSS"
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-129",
              "description": "Improper Validation of Array Index",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-10-27T00:33:58.581Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "tags": [
            "issue-tracking",
            "patch"
          ],
          "url": "https://github.com/ggml-org/llama.cpp/pull/25969"
        },
        {
          "tags": [
            "patch",
            "issue-tracking"
          ],
          "url": "https://github.com/ggml-org/llama.cpp/pull/26511"
        },
        {
          "tags": [
            "patch"
          ],
          "url": "https://github.com/ggml-org/llama.cpp/commit/cf06ad7dfe79e7bf2934150d4fefe1ce8db05490"
        },
        {
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/ggml-org/llama.cpp/blob/b10259/src/llama-vocab.cpp#L1376-L1377"
        },
        {
          "name": "llama.cpp b10261 Release Notes",
          "tags": [
            "release-notes"
          ],
          "url": "https://github.com/ggml-org/llama.cpp/releases/tag/b10261"
        },
        {
          "name": "VulnCheck Advisory: llama.cpp b5899 before b10261 Heap Out-of-Bounds Write via plamo2 Tokenizer",
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/llama-cpp-b5899-before-b10261-heap-out-of-bounds-write-via-plamo2-tokenizer"
        }
      ],
      "title": "llama.cpp b5899 before b10261 Heap Out-of-Bounds Write via plamo2 Tokenizer",
      "x_generator": {
        "engine": "vulncheck-endgame"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-116816",
    "datePublished": "2026-10-27T00:33:58.581Z",
    "dateReserved": "2026-10-26T22:13:56.315Z",
    "dateUpdated": "2026-10-27T00:33:58.581Z",
    "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

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