FKIE_CVE-2024-39720

Vulnerability from fkie_nvd - Published: 2024-10-31 20:15 - Updated: 2025-05-13 13:28
Severity ?
8.2 (High) - CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H
Summary
An issue was discovered in Ollama before 0.1.46. An attacker can use two HTTP requests to upload a malformed GGUF file containing just 4 bytes starting with the GGUF custom magic header. By leveraging a custom Modelfile that includes a FROM statement pointing to the attacker-controlled blob file, the attacker can crash the application through the CreateModel route, leading to a segmentation fault (signal SIGSEGV: segmentation violation).
References
cve@mitre.orghttps://github.com/ollama/ollama/compare/v0.1.45...v0.1.46#diff-782c2737eecfa83b7cb46a77c8bdaf40023e7067baccd4f806ac5517b4563131L417Product
cve@mitre.orghttps://oligo.security/blog/more-models-more-probllmsExploit, Third Party Advisory
Impacted products
Vendor Product Version
ollama ollama *
To clipboard 

{
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:ollama:ollama:*:*:*:*:*:*:*:*",
              "matchCriteriaId": "157D4158-4457-4E02-A24C-BFFD9C2F48D6",
              "versionEndExcluding": "0.1.46",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "An issue was discovered in Ollama before 0.1.46. An attacker can use two HTTP requests to upload a malformed GGUF file containing just 4 bytes starting with the GGUF custom magic header. By leveraging a custom Modelfile that includes a FROM statement pointing to the attacker-controlled blob file, the attacker can crash the application through the CreateModel route, leading to a segmentation fault (signal SIGSEGV: segmentation violation)."
    },
    {
      "lang": "es",
      "value": " Se descubri\u00f3 un problema en Ollama antes de la versi\u00f3n 0.1.46. Un atacante puede usar dos solicitudes HTTP para cargar un archivo GGUF malformado que contenga solo 4 bytes comenzando con el encabezado m\u00e1gico personalizado GGUF. Al aprovechar un Modelfile personalizado que incluye una declaraci\u00f3n FROM que apunta al archivo blob controlado por el atacante, el atacante puede bloquear la aplicaci\u00f3n a trav\u00e9s de la ruta CreateModel, lo que genera una segmentation fault (se\u00f1al SIGSEGV: segmentation violation)."
    }
  ],
  "id": "CVE-2024-39720",
  "lastModified": "2025-05-13T13:28:14.270",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "HIGH",
          "baseScore": 8.2,
          "baseSeverity": "HIGH",
          "confidentialityImpact": "LOW",
          "integrityImpact": "NONE",
          "privilegesRequired": "NONE",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H",
          "version": "3.1"
        },
        "exploitabilityScore": 3.9,
        "impactScore": 4.2,
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "type": "Secondary"
      }
    ]
  },
  "published": "2024-10-31T20:15:04.877",
  "references": [
    {
      "source": "cve@mitre.org",
      "tags": [
        "Product"
      ],
      "url": "https://github.com/ollama/ollama/compare/v0.1.45...v0.1.46#diff-782c2737eecfa83b7cb46a77c8bdaf40023e7067baccd4f806ac5517b4563131L417"
    },
    {
      "source": "cve@mitre.org",
      "tags": [
        "Exploit",
        "Third Party Advisory"
      ],
      "url": "https://oligo.security/blog/more-models-more-probllms"
    }
  ],
  "sourceIdentifier": "cve@mitre.org",
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-125"
        }
      ],
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
      "type": "Secondary"
    }
  ]
}


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.