Vulnerability-Lookup

GHSA-9M9W-53G9-47C4

Vulnerability from github – Published: 2026-05-26 13:30 – Updated: 2026-05-26 13:30

Details

The MLX inference backend in Docker Model Runner on macOS uses the MLX-LM library, which unconditionally imports and executes arbitrary Python files from model directories via the model_file configuration field in config.json. When a model's config.json specifies a model_file pointing to a Python file, MLX-LM uses importlib to load and execute it with no trust_remote_code gate or equivalent safety check. The MLX backend runs without sandboxing, resulting in arbitrary code execution on the Docker host as the Docker Desktop user.

Any container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model from an attacker-controlled OCI registry and request inference.

Severity

8.2 (High)


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

8.8 (High)


                  
                    CVSS:4.0/AV:L/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2026-5843"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-829"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-05-22T20:16:35Z",
    "severity": "HIGH"
  },
  "details": "The MLX inference backend in Docker Model Runner on macOS uses the MLX-LM library, which unconditionally imports and executes arbitrary Python files from model directories via the model_file configuration field in config.json. When a model\u0027s config.json specifies a model_file pointing to a Python file, MLX-LM uses importlib to load and execute it with no trust_remote_code gate or equivalent safety check. The MLX backend runs without sandboxing, resulting in arbitrary code execution on the Docker host as the Docker Desktop user.\n\nAny container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model from an attacker-controlled OCI registry and request inference.",
  "id": "GHSA-9m9w-53g9-47c4",
  "modified": "2026-05-26T13:30:21Z",
  "published": "2026-05-26T13:30:21Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-5843"
    },
    {
      "type": "WEB",
      "url": "https://docs.docker.com/desktop/release-notes/#4710"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:L/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/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",
      "type": "CVSS_V4"
    }
  ]
}

CVE-2026-5843 (GCVE-0-2026-5843)

Vulnerability from cvelistv5 – Published: 2026-05-22 19:28 – Updated: 2026-05-26 14:17

Title

Docker Model Runner container-to-host code execution via MLX-LM model_file importlib loading

Summary

Severity

8.8 (High)


                        
                          CVSS:4.0/AV:L/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H

8.2 (High)


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

CWE

CWE-829 - Inclusion of Functionality from Untrusted Control Sphere

Assigner

Docker

References

1 reference

URL	Tags
https://docs.docker.com/desktop/release-notes/#4710	release-notes

Impacted products

1 product

Vendor	Product	Version
Docker	Docker Desktop	Affected: 4.56.0 , < 4.71.0 (semver)

Credits

David Rochester (@davidrxchester) Nicholas Gould (@gouldnicholas)

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-5843",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-05-26T14:17:01.185739Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-05-26T14:17:24.759Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "platforms": [
            "MacOS"
          ],
          "product": "Docker Desktop",
          "vendor": "Docker",
          "versions": [
            {
              "lessThan": "4.71.0",
              "status": "affected",
              "version": "4.56.0",
              "versionType": "semver"
            }
          ]
        }
      ],
      "configurations": [
        {
          "lang": "en",
          "supportingMedia": [
            {
              "base64": false,
              "type": "text/html",
              "value": "Docker Model Runner enabled with the MLX inference backend on macOS"
            }
          ],
          "value": "Docker Model Runner enabled with the MLX inference backend on macOS"
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "David Rochester (@davidrxchester)"
        },
        {
          "lang": "en",
          "type": "finder",
          "value": "Nicholas Gould (@gouldnicholas)"
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "supportingMedia": [
            {
              "base64": false,
              "type": "text/html",
              "value": "The MLX inference backend in Docker Model Runner on macOS uses the MLX-LM library, which unconditionally imports and executes arbitrary Python files from model directories via the \u003ccode\u003emodel_file\u003c/code\u003e configuration field in \u003ccode\u003econfig.json\u003c/code\u003e. When a model\u0027s \u003ccode\u003econfig.json\u003c/code\u003e specifies a \u003ccode\u003emodel_file\u003c/code\u003e pointing to a Python file, MLX-LM uses \u003ccode\u003eimportlib\u003c/code\u003e to load and execute it with no \u003ccode\u003etrust_remote_code\u003c/code\u003e gate or equivalent safety check. The MLX backend runs without sandboxing, resulting in arbitrary code execution on the Docker host as the Docker Desktop user.\u003cbr\u003e\u003cbr\u003eAny container on the Docker network can trigger this by calling the \u003ccode\u003emodel-runner.docker.internal\u003c/code\u003e API to pull a malicious model from an attacker-controlled OCI registry and request inference."
            }
          ],
          "value": "The MLX inference backend in Docker Model Runner on macOS uses the MLX-LM library, which unconditionally imports and executes arbitrary Python files from model directories via the model_file configuration field in config.json. When a model\u0027s config.json specifies a model_file pointing to a Python file, MLX-LM uses importlib to load and execute it with no trust_remote_code gate or equivalent safety check. The MLX backend runs without sandboxing, resulting in arbitrary code execution on the Docker host as the Docker Desktop user.\n\nAny container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model from an attacker-controlled OCI registry and request inference."
        }
      ],
      "impacts": [
        {
          "capecId": "CAPEC-480",
          "descriptions": [
            {
              "lang": "en",
              "value": "CAPEC-480 Escaping Virtualization"
            }
          ]
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "PRESENT",
            "attackVector": "LOCAL",
            "baseScore": 8.8,
            "baseSeverity": "HIGH",
            "exploitMaturity": "NOT_DEFINED",
            "privilegesRequired": "LOW",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "HIGH",
            "subConfidentialityImpact": "HIGH",
            "subIntegrityImpact": "HIGH",
            "userInteraction": "NONE",
            "valueDensity": "NOT_DEFINED",
            "vectorString": "CVSS:4.0/AV:L/AC:L/AT:P/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "HIGH",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        },
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "LOCAL",
            "availabilityImpact": "HIGH",
            "baseScore": 8.2,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "LOW",
            "scope": "CHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H",
            "version": "3.1"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-829",
              "description": "CWE-829: Inclusion of Functionality from Untrusted Control Sphere",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-05-22T19:28:38.857Z",
        "orgId": "686469e6-3ff6-451b-ab8b-cf5b9e89401e",
        "shortName": "Docker"
      },
      "references": [
        {
          "tags": [
            "release-notes"
          ],
          "url": "https://docs.docker.com/desktop/release-notes/#4710"
        }
      ],
      "source": {
        "discovery": "EXTERNAL"
      },
      "title": "Docker Model Runner container-to-host code execution via MLX-LM model_file importlib loading",
      "workarounds": [
        {
          "lang": "en",
          "supportingMedia": [
            {
              "base64": false,
              "type": "text/html",
              "value": "Disable Docker Model Runner or only run trusted containers on Docker Desktop instances where Model Runner is enabled."
            }
          ],
          "value": "Disable Docker Model Runner or only run trusted containers on Docker Desktop instances where Model Runner is enabled."
        }
      ],
      "x_generator": {
        "engine": "Vulnogram 0.2.0"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "686469e6-3ff6-451b-ab8b-cf5b9e89401e",
    "assignerShortName": "Docker",
    "cveId": "CVE-2026-5843",
    "datePublished": "2026-05-22T19:28:38.857Z",
    "dateReserved": "2026-04-08T17:43:50.508Z",
    "dateUpdated": "2026-05-26T14:17:24.759Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

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.

Detection rules are retrieved from Rulezet.

Action not permitted

GHSA-9M9W-53G9-47C4

CVE-2026-5843 (GCVE-0-2026-5843)

Tags

Sightings

Nomenclature