Vulnerability-Lookup

UBUNTU-CVE-2026-34159 (CVE-2026-34159)

Vulnerability from osv_ubuntu – Published: 2026-04-01 18:16 – Updated: 2026-05-14 11:40 – Source website

Details

llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages. Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been patched in version b8492.

Severity

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

URL

Type

	https://ubuntu.com/security/CVE-2026-34159	REPORT
	https://www.cve.org/CVERecord?id=CVE-2026-34159	REPORT
	https://github.com/ggml-org/llama.cpp/security/ad…	REPORT
	https://github.com/ggml-org/llama.cpp/pull/20908	REPORT

JSON

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"
      ]
    }
  ],
  "aliases": [],
  "details": "llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend\u0027s deserialize_tensor() skips all bounds validation when a tensor\u0027s buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages. Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been patched in version b8492.",
  "id": "UBUNTU-CVE-2026-34159",
  "modified": "2026-05-14T11:40:56Z",
  "published": "2026-04-01T18:16:00Z",
  "references": [
    {
      "type": "REPORT",
      "url": "https://ubuntu.com/security/CVE-2026-34159"
    },
    {
      "type": "REPORT",
      "url": "https://www.cve.org/CVERecord?id=CVE-2026-34159"
    },
    {
      "type": "REPORT",
      "url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw"
    },
    {
      "type": "REPORT",
      "url": "https://github.com/ggml-org/llama.cpp/pull/20908"
    }
  ],
  "related": [],
  "schema_version": "1.7.0",
  "severity": [
    {
      "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-2026-34159"
  ]
}

CVE-2026-34159 (GCVE-0-2026-34159)

Vulnerability from cvelistv5 – Published: 2026-04-01 16:59 – Updated: 2026-04-02 03:56

Title

llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend

Summary

Severity

9.8 (Critical)


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

SSVC

Exploitation: poc Automatable: yes Technical Impact: total

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-04-01 00:00 UTC

CWE

CWE-119 - Improper Restriction of Operations within the Bounds of a Memory Buffer

Assigner

GitHub_M mitre root

References

3 references

URL	Tags
https://github.com/ggml-org/llama.cpp/security/ad…	x_refsource_CONFIRM
https://github.com/ggml-org/llama.cpp/pull/20908	x_refsource_MISC
https://github.com/ggml-org/llama.cpp/commit/39bf…	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version
ggml-org	llama.cpp	Affected: < b8492

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-34159",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-04-01T00:00:00+00:00",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-04-02T03:56:11.820Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "llama.cpp",
          "vendor": "ggml-org",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c b8492"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend\u0027s deserialize_tensor() skips all bounds validation when a tensor\u0027s buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages. Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been patched in version b8492."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "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"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-119",
              "description": "CWE-119: Improper Restriction of Operations within the Bounds of a Memory Buffer",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-04-01T16:59:59.967Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw"
        },
        {
          "name": "https://github.com/ggml-org/llama.cpp/pull/20908",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/ggml-org/llama.cpp/pull/20908"
        },
        {
          "name": "https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042"
        }
      ],
      "source": {
        "advisory": "GHSA-j8rj-fmpv-wcxw",
        "discovery": "UNKNOWN"
      },
      "title": "llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-34159",
    "datePublished": "2026-04-01T16:59:59.967Z",
    "dateReserved": "2026-03-25T20:12:04.197Z",
    "dateUpdated": "2026-04-02T03:56:11.820Z",
    "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.

Detection rules are retrieved from Rulezet.

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.