Vulnerability-Lookup

UBUNTU-CVE-2025-49847 (CVE-2025-49847)

Vulnerability from osv_ubuntu – Published: 2025-06-17 20:15 – Updated: 2026-05-20 15:22 – Source website

Details

llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker‐supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp’s vocabulary‐loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length < (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662.

Severity

8.8 (High)


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

N/A (UNKNOWN)


                    
                      medium

References

URL

Type

	https://ubuntu.com/security/CVE-2025-49847	REPORT
	https://www.cve.org/CVERecord?id=CVE-2025-49847	REPORT
	https://github.com/ggml-org/llama.cpp/security/ad…	REPORT
	https://github.com/ggml-org/llama.cpp/commit/3cfb…	REPORT
	https://github.com/ggml-org/llama.cpp/commit/3cfb…	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"
      ]
    },
    {
      "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++. Prior to version b5662, an attacker\u2010supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp\u2019s vocabulary\u2010loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length \u003c (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662.",
  "id": "UBUNTU-CVE-2025-49847",
  "modified": "2026-05-20T15:22:53Z",
  "published": "2025-06-17T20:15:00Z",
  "references": [
    {
      "type": "REPORT",
      "url": "https://ubuntu.com/security/CVE-2025-49847"
    },
    {
      "type": "REPORT",
      "url": "https://www.cve.org/CVERecord?id=CVE-2025-49847"
    },
    {
      "type": "REPORT",
      "url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqr"
    },
    {
      "type": "REPORT",
      "url": "https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5"
    },
    {
      "type": "REPORT",
      "url": "https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5"
    }
  ],
  "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": "medium",
      "type": "Ubuntu"
    }
  ],
  "upstream": [
    "CVE-2025-49847"
  ]
}

CVE-2025-49847 (GCVE-0-2025-49847)

Vulnerability from cvelistv5 – Published: 2025-06-17 20:04 – Updated: 2025-06-18 13:41

Title

llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model

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 2025-06-18 13:40 UTC

CWE

CWE-119 - Improper Restriction of Operations within the Bounds of a Memory Buffer
CWE-195 - Signed to Unsigned Conversion Error

Assigner

GitHub_M mitre root Scorecard

References

2 references

URL	Tags
https://github.com/ggml-org/llama.cpp/security/ad…	x_refsource_CONFIRM
https://github.com/ggml-org/llama.cpp/commit/3cfb…	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version
ggml-org	llama.cpp	Affected: < b5662

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2025-49847",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2025-06-18T13:40:43.172535Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2025-06-18T13:41:11.407Z",
          "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 b5662"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker\u2010supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp\u2019s vocabulary\u2010loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length \u003c (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662."
        }
      ],
      "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-119",
              "description": "CWE-119: Improper Restriction of Operations within the Bounds of a Memory Buffer",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-195",
              "description": "CWE-195: Signed to Unsigned Conversion Error",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2025-06-17T20:04:40.893Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqr",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqr"
        },
        {
          "name": "https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5"
        }
      ],
      "source": {
        "advisory": "GHSA-8wwf-w4qm-gpqr",
        "discovery": "UNKNOWN"
      },
      "title": "llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2025-49847",
    "datePublished": "2025-06-17T20:04:40.893Z",
    "dateReserved": "2025-06-11T14:33:57.800Z",
    "dateUpdated": "2025-06-18T13:41:11.407Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1"
}

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.

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

UBUNTU-CVE-2025-49847 (CVE-2025-49847)

CVE-2025-49847 (GCVE-0-2025-49847)

Tags

Sightings

Nomenclature

Related by attack behaviour