CVE-2024-39720 (GCVE-0-2024-39720)
Vulnerability from cvelistv5
Published
2024-10-31 00:00
Modified
2024-11-01 15:20
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-782c2737eecfa83b7cb46a77c8bdaf40023e7067baccd4f806ac5517b4563131L417
cve@mitre.orghttps://oligo.security/blog/more-models-more-probllms
Impacted products
Vendor Product Version
n/a n/a Version: n/a
Show details on NVD website

To clipboard 

{
   containers: {
      adp: [
         {
            affected: [
               {
                  cpes: [
                     "cpe:2.3:a:ollama:ollama:*:*:*:*:*:*:*:*",
                  ],
                  defaultStatus: "unknown",
                  product: "ollama",
                  vendor: "ollama",
                  versions: [
                     {
                        lessThan: "0.1.46",
                        status: "affected",
                        version: "0",
                        versionType: "custom",
                     },
                  ],
               },
            ],
            metrics: [
               {
                  cvssV3_1: {
                     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",
                  },
               },
               {
                  other: {
                     content: {
                        id: "CVE-2024-39720",
                        options: [
                           {
                              Exploitation: "poc",
                           },
                           {
                              Automatable: "yes",
                           },
                           {
                              "Technical Impact": "partial",
                           },
                        ],
                        role: "CISA Coordinator",
                        timestamp: "2024-11-01T15:18:50.666671Z",
                        version: "2.0.3",
                     },
                     type: "ssvc",
                  },
               },
            ],
            problemTypes: [
               {
                  descriptions: [
                     {
                        cweId: "CWE-125",
                        description: "CWE-125 Out-of-bounds Read",
                        lang: "en",
                        type: "CWE",
                     },
                  ],
               },
            ],
            providerMetadata: {
               dateUpdated: "2024-11-01T15:20:12.939Z",
               orgId: "134c704f-9b21-4f2e-91b3-4a467353bcc0",
               shortName: "CISA-ADP",
            },
            title: "CISA ADP Vulnrichment",
         },
      ],
      cna: {
         affected: [
            {
               product: "n/a",
               vendor: "n/a",
               versions: [
                  {
                     status: "affected",
                     version: "n/a",
                  },
               ],
            },
         ],
         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).",
            },
         ],
         problemTypes: [
            {
               descriptions: [
                  {
                     description: "n/a",
                     lang: "en",
                     type: "text",
                  },
               ],
            },
         ],
         providerMetadata: {
            dateUpdated: "2024-11-01T13:44:48.589574",
            orgId: "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
            shortName: "mitre",
         },
         references: [
            {
               url: "https://github.com/ollama/ollama/compare/v0.1.45...v0.1.46#diff-782c2737eecfa83b7cb46a77c8bdaf40023e7067baccd4f806ac5517b4563131L417",
            },
            {
               url: "https://oligo.security/blog/more-models-more-probllms",
            },
         ],
      },
   },
   cveMetadata: {
      assignerOrgId: "8254265b-2729-46b6-b9e3-3dfca2d5bfca",
      assignerShortName: "mitre",
      cveId: "CVE-2024-39720",
      datePublished: "2024-10-31T00:00:00",
      dateReserved: "2024-06-28T00:00:00",
      dateUpdated: "2024-11-01T15:20:12.939Z",
      state: "PUBLISHED",
   },
   dataType: "CVE_RECORD",
   dataVersion: "5.1",
   "vulnerability-lookup:meta": {
      fkie_nvd: {
         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: "2024-11-01T16:35:23.210",
         metrics: "{\"cvssMetricV31\": [{\"source\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"type\": \"Secondary\", \"cvssData\": {\"version\": \"3.1\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H\", \"baseScore\": 8.2, \"baseSeverity\": \"HIGH\", \"attackVector\": \"NETWORK\", \"attackComplexity\": \"LOW\", \"privilegesRequired\": \"NONE\", \"userInteraction\": \"NONE\", \"scope\": \"UNCHANGED\", \"confidentialityImpact\": \"LOW\", \"integrityImpact\": \"NONE\", \"availabilityImpact\": \"HIGH\"}, \"exploitabilityScore\": 3.9, \"impactScore\": 4.2}]}",
         published: "2024-10-31T20:15:04.877",
         references: "[{\"url\": \"https://github.com/ollama/ollama/compare/v0.1.45...v0.1.46#diff-782c2737eecfa83b7cb46a77c8bdaf40023e7067baccd4f806ac5517b4563131L417\", \"source\": \"cve@mitre.org\"}, {\"url\": \"https://oligo.security/blog/more-models-more-probllms\", \"source\": \"cve@mitre.org\"}]",
         sourceIdentifier: "cve@mitre.org",
         vulnStatus: "Awaiting Analysis",
         weaknesses: "[{\"source\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"type\": \"Secondary\", \"description\": [{\"lang\": \"en\", \"value\": \"CWE-125\"}]}]",
      },
      nvd: "{\"cve\":{\"id\":\"CVE-2024-39720\",\"sourceIdentifier\":\"cve@mitre.org\",\"published\":\"2024-10-31T20:15:04.877\",\"lastModified\":\"2024-11-01T16:35:23.210\",\"vulnStatus\":\"Awaiting Analysis\",\"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 descubrió un problema en Ollama antes de la versión 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 mágico personalizado GGUF. Al aprovechar un Modelfile personalizado que incluye una declaración FROM que apunta al archivo blob controlado por el atacante, el atacante puede bloquear la aplicación a través de la ruta CreateModel, lo que genera una segmentation fault (señal SIGSEGV: segmentation violation).\"}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H\",\"baseScore\":8.2,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"LOW\",\"integrityImpact\":\"NONE\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":3.9,\"impactScore\":4.2}]},\"weaknesses\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-125\"}]}],\"references\":[{\"url\":\"https://github.com/ollama/ollama/compare/v0.1.45...v0.1.46#diff-782c2737eecfa83b7cb46a77c8bdaf40023e7067baccd4f806ac5517b4563131L417\",\"source\":\"cve@mitre.org\"},{\"url\":\"https://oligo.security/blog/more-models-more-probllms\",\"source\":\"cve@mitre.org\"}]}}",
      vulnrichment: {
         containers: "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 8.2, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H\", \"integrityImpact\": \"NONE\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"LOW\"}}, {\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2024-39720\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"yes\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2024-11-01T15:18:50.666671Z\"}}}], \"affected\": [{\"cpes\": [\"cpe:2.3:a:ollama:ollama:*:*:*:*:*:*:*:*\"], \"vendor\": \"ollama\", \"product\": \"ollama\", \"versions\": [{\"status\": \"affected\", \"version\": \"0\", \"lessThan\": \"0.1.46\", \"versionType\": \"custom\"}], \"defaultStatus\": \"unknown\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-125\", \"description\": \"CWE-125 Out-of-bounds Read\"}]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2024-11-01T15:20:03.231Z\"}}], \"cna\": {\"affected\": [{\"vendor\": \"n/a\", \"product\": \"n/a\", \"versions\": [{\"status\": \"affected\", \"version\": \"n/a\"}]}], \"references\": [{\"url\": \"https://github.com/ollama/ollama/compare/v0.1.45...v0.1.46#diff-782c2737eecfa83b7cb46a77c8bdaf40023e7067baccd4f806ac5517b4563131L417\"}, {\"url\": \"https://oligo.security/blog/more-models-more-probllms\"}], \"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).\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"text\", \"description\": \"n/a\"}]}], \"providerMetadata\": {\"orgId\": \"8254265b-2729-46b6-b9e3-3dfca2d5bfca\", \"shortName\": \"mitre\", \"dateUpdated\": \"2024-11-01T13:44:48.589574\"}}}",
         cveMetadata: "{\"cveId\": \"CVE-2024-39720\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2024-11-01T15:20:12.939Z\", \"dateReserved\": \"2024-06-28T00:00:00\", \"assignerOrgId\": \"8254265b-2729-46b6-b9e3-3dfca2d5bfca\", \"datePublished\": \"2024-10-31T00:00:00\", \"assignerShortName\": \"mitre\"}",
         dataType: "CVE_RECORD",
         dataVersion: "5.1",
      },
   },
}


Log in or create an account to share your comment.

Security Advisory comment format.

This schema specifies the format of a comment related to a security advisory.

UUIDv4 of the comment
UUIDv4 of the Vulnerability-Lookup instance
When the comment was created originally
When the comment was last updated
Title of the comment
Description of the comment
The identifier of the vulnerability (CVE ID, GHSA-ID, PYSEC ID, etc.).



Tags
Taxonomy of the tags.




Sightings

Author Source Type Date

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or seen somewhere by the user.
  • Confirmed: The vulnerability is confirmed from an analyst perspective.
  • Exploited: This vulnerability was exploited and seen by the user reporting the sighting.
  • Patched: This vulnerability was successfully patched by the user reporting the sighting.
  • Not exploited: This vulnerability was not exploited or seen by the user reporting the sighting.
  • Not confirmed: The user expresses doubt about the veracity of the vulnerability.
  • Not patched: This vulnerability was not successfully patched by the user reporting the sighting.