FKIE_CVE-2026-7482

Vulnerability from fkie_nvd - Published: 2026-05-04 13:16 - Updated: 2026-11-11 23:10
Summary
Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file's actual length; during quantization in fs/ggml/gguf.go and server/quantization.go (WriteTo()), the server reads past the allocated heap buffer. The leaked memory contents may include environment variables, API keys, system prompts, and concurrent users' conversation data, and can be exfiltrated by uploading the resulting model artifact through the /api/push endpoint to an attacker-controlled registry. The /api/create and /api/push endpoints have no authentication in the upstream distribution. Default deployments bind to 127.0.0.1, but the documented OLLAMA_HOST=0.0.0.0 configuration is widely used in practice (large public-internet exposure observed).
Impacted products
Vendor Product Version
ollama ollama *

{
  "affected": [
    {
      "affectedData": [
        {
          "collectionURL": "https://github.com",
          "defaultStatus": "unaffected",
          "packageName": "ollama/ollama",
          "product": "ollama",
          "programFiles": [
            "fs/ggml/gguf.go",
            "server/quantization.go"
          ],
          "repo": "https://github.com/ollama/ollama",
          "vendor": "ollama",
          "versions": [
            {
              "lessThan": "0.17.1",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            }
          ]
        }
      ],
      "source": "abd028dc-c042-4c4d-9749-38d0f850af89"
    }
  ],
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:ollama:ollama:*:*:*:*:*:*:*:*",
              "matchCriteriaId": "18CE34C3-1F67-46CE-8B8D-5B54FC3996EF",
              "versionEndExcluding": "0.17.1",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file\u0027s actual length; during quantization in fs/ggml/gguf.go and server/quantization.go (WriteTo()), the server reads past the allocated heap buffer. The leaked memory contents may include environment variables, API keys, system prompts, and concurrent users\u0027 conversation data, and can be exfiltrated by uploading the resulting model artifact through the /api/push endpoint to an attacker-controlled registry. The /api/create and /api/push endpoints have no authentication in the upstream distribution. Default deployments bind to 127.0.0.1, but the documented OLLAMA_HOST=0.0.0.0 configuration is widely used in practice (large public-internet exposure observed)."
    },
    {
      "lang": "es",
      "value": "Ollama anterior a 0.17.1 contiene una vulnerabilidad de lectura fuera de l\u00edmites del heap en el cargador de modelos GGUF. El endpoint /api/create acepta un archivo GGUF proporcionado por un atacante en el que el desplazamiento y el tama\u00f1o del tensor declarados exceden la longitud real del archivo; durante la cuantificaci\u00f3n en fs/ggml/gguf.go y server/quantization.go (WriteTo()), el servidor lee m\u00e1s all\u00e1 del b\u00fafer de heap asignado. El contenido de la memoria filtrada puede incluir variables de entorno, claves API, prompts del sistema y datos de conversaci\u00f3n de usuarios concurrentes, y puede ser exfiltrado al cargar el artefacto del modelo resultante a trav\u00e9s del endpoint /api/push a un registro controlado por un atacante. Los endpoints /api/create y /api/push no tienen autenticaci\u00f3n en la distribuci\u00f3n upstream. Las implementaciones predeterminadas se enlazan a 127.0.0.1, pero la configuraci\u00f3n documentada OLLAMA_HOST=0.0.0.0 es ampliamente utilizada en la pr\u00e1ctica (se observa una gran exposici\u00f3n a internet p\u00fablica)."
    }
  ],
  "id": "CVE-2026-7482",
  "lastModified": "2026-11-11T23:10:00.263",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "HIGH",
          "baseScore": 9.1,
          "baseSeverity": "CRITICAL",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "NONE",
          "privilegesRequired": "NONE",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H",
          "version": "3.1"
        },
        "exploitabilityScore": 3.9,
        "impactScore": 5.2,
        "source": "abd028dc-c042-4c4d-9749-38d0f850af89",
        "type": "Secondary"
      }
    ],
    "cvssMetricV40": [
      {
        "cvssData": {
          "Automatable": "YES",
          "Recovery": "AUTOMATIC",
          "Safety": "NOT_DEFINED",
          "attackComplexity": "LOW",
          "attackRequirements": "NONE",
          "attackVector": "NETWORK",
          "availabilityRequirement": "NOT_DEFINED",
          "baseScore": 8.8,
          "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": "RED",
          "subAvailabilityImpact": "NONE",
          "subConfidentialityImpact": "NONE",
          "subIntegrityImpact": "NONE",
          "userInteraction": "NONE",
          "valueDensity": "DIFFUSE",
          "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/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:Y/R:A/V:D/RE:L/U:Red",
          "version": "4.0",
          "vulnAvailabilityImpact": "HIGH",
          "vulnConfidentialityImpact": "HIGH",
          "vulnIntegrityImpact": "NONE",
          "vulnerabilityResponseEffort": "LOW"
        },
        "source": "abd028dc-c042-4c4d-9749-38d0f850af89",
        "type": "Secondary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-7482",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2026-05-04T13:48:32.181054Z",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2026-05-04T13:16:01.727",
  "references": [
    {
      "source": "abd028dc-c042-4c4d-9749-38d0f850af89",
      "tags": [
        "Patch"
      ],
      "url": "https://github.com/ollama/ollama/commit/88d57d0483cca907e0b23a968c83627a20b21047"
    },
    {
      "source": "abd028dc-c042-4c4d-9749-38d0f850af89",
      "tags": [
        "Issue Tracking",
        "Patch"
      ],
      "url": "https://github.com/ollama/ollama/pull/14406"
    },
    {
      "source": "abd028dc-c042-4c4d-9749-38d0f850af89",
      "tags": [
        "Release Notes"
      ],
      "url": "https://github.com/ollama/ollama/releases/tag/v0.17.1"
    }
  ],
  "sourceIdentifier": "abd028dc-c042-4c4d-9749-38d0f850af89",
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-125"
        }
      ],
      "source": "abd028dc-c042-4c4d-9749-38d0f850af89",
      "type": "Secondary"
    }
  ]
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.


Loading…

Loading…

Loading…

Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.

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.
Vulnerability timeline

Sightings and recorded dates, grouped by day · UTC

JSON
How durations are calculated

Following the VTEM framework (Black Hat USA 2015), time to patch starts when the vendor or a coordinator was informed, total time to patch at discovery, and disclosure to patch at public disclosure; vendor response time runs from the report to its acknowledgement. Time to exploit and time unpatched start at the earliest discovery or report, falling back to public disclosure. Unpatched time ends at the first recorded patch, or the calculation time when no patch is recorded. Exploitation to patch shows the interval between those two events; a published proof of concept is a public exploit, not exploitation.

Each result shows its source dates. A negative interval means the end event came first; when date-only inputs leave the order open, the result says so. Date-only inputs are approximate. The earliest evidence wins: KEV report dates and sightings are labelled as such. Records describing another vulnerability are listed but never calculated from, and a PoC alone does not establish exploitation. Missing patch evidence does not prove that no patch exists. Filters below change the event list only.

Events included in the timeline

Loading timeline…


    Loading…

    Loading…

    Loading…

    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.