UBUNTU-CVE-2026-21869 (CVE-2026-21869)

Vulnerability from osv_ubuntu – Published: 2026-01-08 00:16 – Updated: 2026-05-20 15:24 – Source website
VLAI
Details

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)
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
N/A (UNKNOWN)
medium
References
To clipboard 

{
  "affected": [
    {
      "ecosystem_specific": {
        "binaries": [
          {
            "binary_name": "llama.cpp",
            "binary_version": "5882+dfsg-2"
          }
        ]
      },
      "package": {
        "ecosystem": "Ubuntu:25.10",
        "name": "llama.cpp",
        "purl": "pkg:deb/ubuntu/llama.cpp@5882+dfsg-2?arch=source\u0026distro=questing"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "5318+dfsg-1",
        "5318+dfsg-2",
        "5713+dfsg-1",
        "5760+dfsg-1",
        "5760+dfsg-3",
        "5760+dfsg-4",
        "5882+dfsg-2"
      ]
    },
    {
      "ecosystem_specific": {
        "binaries": [
          {
            "binary_name": "libllama0",
            "binary_version": "8681+dfsg-1"
          },
          {
            "binary_name": "llama.cpp",
            "binary_version": "8681+dfsg-1"
          },
          {
            "binary_name": "llama.cpp-examples",
            "binary_version": "8681+dfsg-1"
          },
          {
            "binary_name": "llama.cpp-tests",
            "binary_version": "8681+dfsg-1"
          },
          {
            "binary_name": "llama.cpp-tools",
            "binary_version": "8681+dfsg-1"
          },
          {
            "binary_name": "llama.cpp-tools-extra",
            "binary_version": "8681+dfsg-1"
          },
          {
            "binary_name": "python3-gguf",
            "binary_version": "8681+dfsg-1"
          }
        ]
      },
      "package": {
        "ecosystem": "Ubuntu:26.04:LTS",
        "name": "llama.cpp",
        "purl": "pkg:deb/ubuntu/llama.cpp@8681+dfsg-1?arch=source\u0026distro=resolute"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "5882+dfsg-2",
        "8064+dfsg-1ubuntu1",
        "8681+dfsg-1"
      ]
    }
  ],
  "aliases": [],
  "details": "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.",
  "id": "UBUNTU-CVE-2026-21869",
  "modified": "2026-05-20T15:24:36Z",
  "published": "2026-01-08T00:16:00Z",
  "references": [
    {
      "type": "REPORT",
      "url": "https://ubuntu.com/security/CVE-2026-21869"
    },
    {
      "type": "REPORT",
      "url": "https://www.cve.org/CVERecord?id=CVE-2026-21869"
    },
    {
      "type": "REPORT",
      "url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8947-pfff-2f3c"
    }
  ],
  "related": [],
  "schema_version": "1.7.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    },
    {
      "score": "medium",
      "type": "Ubuntu"
    }
  ],
  "upstream": [
    "CVE-2026-21869"
  ]
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

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.



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.