FKIE_CVE-2025-15514

Vulnerability from fkie_nvd - Published: 2026-01-12 23:15 - Updated: 2026-01-21 17:52
Severity ?
7.5 (High) - CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Summary
Ollama 0.11.5-rc0 through current version 0.13.5 contain a null pointer dereference vulnerability in the multi-modal model image processing functionality. When processing base64-encoded image data via the /api/chat endpoint, the application fails to validate that the decoded data represents valid media before passing it to the mtmd_helper_bitmap_init_from_buf function. This function can return NULL for malformed input, but the code does not check this return value before dereferencing the pointer in subsequent operations. A remote attacker can exploit this by sending specially crafted base64 image data that decodes to invalid media, causing a segmentation fault and crashing the runner process. This results in a denial of service condition where the model becomes unavailable to all users until the service is restarted.
References
disclosure@vulncheck.comhttps://https://github.com/ollama/ollamaProduct
disclosure@vulncheck.comhttps://huntr.com/bounties/172df98b-07cd-41ea-a628-366f8cd525c0Exploit, Patch, Third Party Advisory
disclosure@vulncheck.comhttps://ollama.com/Product
disclosure@vulncheck.comhttps://www.vulncheck.com/advisories/ollama-multi-modal-image-processing-null-pointer-dereferenceThird Party Advisory
Impacted products
Vendor Product Version
ollama ollama *
ollama ollama 0.11.5
ollama ollama 0.11.5
ollama ollama 0.11.5
ollama ollama 0.11.5
ollama ollama 0.11.5
ollama ollama 0.11.5
ollama ollama 0.11.5
To clipboard 

{
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:ollama:ollama:*:-:*:*:*:*:*:*",
              "matchCriteriaId": "A2EB10B7-A5EB-4B01-A591-C27DEA897FF6",
              "versionEndIncluding": "0.13.5",
              "versionStartIncluding": "0.11.6",
              "vulnerable": true
            },
            {
              "criteria": "cpe:2.3:a:ollama:ollama:0.11.5:-:*:*:*:*:*:*",
              "matchCriteriaId": "AC72C651-C41F-4C69-BADF-9C0F2E722F20",
              "vulnerable": true
            },
            {
              "criteria": "cpe:2.3:a:ollama:ollama:0.11.5:rc0:*:*:*:*:*:*",
              "matchCriteriaId": "7B2DAD56-4180-4D74-ABAE-34946D2619D0",
              "vulnerable": true
            },
            {
              "criteria": "cpe:2.3:a:ollama:ollama:0.11.5:rc1:*:*:*:*:*:*",
              "matchCriteriaId": "723E4B33-FCAB-4052-B83F-E8CA13B0C6C5",
              "vulnerable": true
            },
            {
              "criteria": "cpe:2.3:a:ollama:ollama:0.11.5:rc2:*:*:*:*:*:*",
              "matchCriteriaId": "073B24E6-AD43-4186-A4F7-1CC95F93F47B",
              "vulnerable": true
            },
            {
              "criteria": "cpe:2.3:a:ollama:ollama:0.11.5:rc3:*:*:*:*:*:*",
              "matchCriteriaId": "6194878B-E3B9-43C5-8B3F-37F423A720EC",
              "vulnerable": true
            },
            {
              "criteria": "cpe:2.3:a:ollama:ollama:0.11.5:rc4:*:*:*:*:*:*",
              "matchCriteriaId": "3D7F97D1-1C4A-4F41-BBB9-D147E8B3CFE1",
              "vulnerable": true
            },
            {
              "criteria": "cpe:2.3:a:ollama:ollama:0.11.5:rc5:*:*:*:*:*:*",
              "matchCriteriaId": "686D5C2C-42B1-4C97-9497-3EF9020B9B83",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "Ollama 0.11.5-rc0 through current version 0.13.5 contain a null pointer dereference vulnerability in the multi-modal model image processing functionality. When processing base64-encoded image data via the /api/chat endpoint, the application fails to validate that the decoded data represents valid media before passing it to the mtmd_helper_bitmap_init_from_buf function. This function can return NULL for malformed input, but the code does not check this return value before dereferencing the pointer in subsequent operations. A remote attacker can exploit this by sending specially crafted base64 image data that decodes to invalid media, causing a segmentation fault and crashing the runner process. This results in a denial of service condition where the model becomes unavailable to all users until the service is restarted."
    },
    {
      "lang": "es",
      "value": "Ollama 0.11.5-rc0 hasta la versi\u00f3n actual 0.13.5 contienen una vulnerabilidad de desreferencia de puntero nulo en la funcionalidad de procesamiento de im\u00e1genes del modelo multimodal. Al procesar datos de imagen codificados en base64 a trav\u00e9s del endpoint /api/chat, la aplicaci\u00f3n no valida que los datos decodificados representen medios v\u00e1lidos antes de pasarlos a la funci\u00f3n mtmd_helper_bitmap_init_from_buf. Esta funci\u00f3n puede devolver NULL para entradas malformadas, pero el c\u00f3digo no verifica este valor de retorno antes de desreferenciar el puntero en operaciones posteriores. Un atacante remoto puede explotar esto enviando datos de imagen base64 especialmente dise\u00f1ados que se decodifican a medios no v\u00e1lidos, causando un fallo de segmentaci\u00f3n y bloqueando el proceso del ejecutor. Esto resulta en una condici\u00f3n de denegaci\u00f3n de servicio donde el modelo deja de estar disponible para todos los usuarios hasta que se reinicie el servicio."
    }
  ],
  "id": "CVE-2025-15514",
  "lastModified": "2026-01-21T17:52:04.980",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "HIGH",
          "baseScore": 7.5,
          "baseSeverity": "HIGH",
          "confidentialityImpact": "NONE",
          "integrityImpact": "NONE",
          "privilegesRequired": "NONE",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
          "version": "3.1"
        },
        "exploitabilityScore": 3.9,
        "impactScore": 3.6,
        "source": "nvd@nist.gov",
        "type": "Primary"
      }
    ],
    "cvssMetricV40": [
      {
        "cvssData": {
          "Automatable": "NOT_DEFINED",
          "Recovery": "NOT_DEFINED",
          "Safety": "NOT_DEFINED",
          "attackComplexity": "LOW",
          "attackRequirements": "NONE",
          "attackVector": "NETWORK",
          "availabilityRequirement": "NOT_DEFINED",
          "baseScore": 8.7,
          "baseSeverity": "HIGH",
          "confidentialityRequirement": "NOT_DEFINED",
          "exploitMaturity": "NOT_DEFINED",
          "integrityRequirement": "NOT_DEFINED",
          "modifiedAttackComplexity": "NOT_DEFINED",
          "modifiedAttackRequirements": "NOT_DEFINED",
          "modifiedAttackVector": "NOT_DEFINED",
          "modifiedPrivilegesRequired": "NOT_DEFINED",
          "modifiedSubAvailabilityImpact": "NOT_DEFINED",
          "modifiedSubConfidentialityImpact": "NOT_DEFINED",
          "modifiedSubIntegrityImpact": "NOT_DEFINED",
          "modifiedUserInteraction": "NOT_DEFINED",
          "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
          "modifiedVulnConfidentialityImpact": "NOT_DEFINED",
          "modifiedVulnIntegrityImpact": "NOT_DEFINED",
          "privilegesRequired": "NONE",
          "providerUrgency": "NOT_DEFINED",
          "subAvailabilityImpact": "NONE",
          "subConfidentialityImpact": "NONE",
          "subIntegrityImpact": "NONE",
          "userInteraction": "NONE",
          "valueDensity": "NOT_DEFINED",
          "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/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",
          "version": "4.0",
          "vulnAvailabilityImpact": "HIGH",
          "vulnConfidentialityImpact": "NONE",
          "vulnIntegrityImpact": "NONE",
          "vulnerabilityResponseEffort": "NOT_DEFINED"
        },
        "source": "disclosure@vulncheck.com",
        "type": "Secondary"
      }
    ]
  },
  "published": "2026-01-12T23:15:51.957",
  "references": [
    {
      "source": "disclosure@vulncheck.com",
      "tags": [
        "Product"
      ],
      "url": "https://https://github.com/ollama/ollama"
    },
    {
      "source": "disclosure@vulncheck.com",
      "tags": [
        "Exploit",
        "Patch",
        "Third Party Advisory"
      ],
      "url": "https://huntr.com/bounties/172df98b-07cd-41ea-a628-366f8cd525c0"
    },
    {
      "source": "disclosure@vulncheck.com",
      "tags": [
        "Product"
      ],
      "url": "https://ollama.com/"
    },
    {
      "source": "disclosure@vulncheck.com",
      "tags": [
        "Third Party Advisory"
      ],
      "url": "https://www.vulncheck.com/advisories/ollama-multi-modal-image-processing-null-pointer-dereference"
    }
  ],
  "sourceIdentifier": "disclosure@vulncheck.com",
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-395"
        }
      ],
      "source": "disclosure@vulncheck.com",
      "type": "Primary"
    }
  ]
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Sightings

Author Source Type Date

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.