CVE-2026-5817

The vllm-metal inference backend in Docker Model Runner on macOS unconditionally sets trust_remote_code=True when loading model tokenizers, and runs without sandboxing. This causes transformers.AutoTokenizer.from_pretrained() to import and execute arbitrary Python files included in any model pulled from an OCI registry, resulting in arbitrary code execution on the Docker host as the Docker Desktop user when inference is triggered. Any container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model and request inference.

CVSS v3 8.2 HIGH

8.2^/10

CVSS v3 : HIGH

Vector :

Exploitability : 1.5 / Impact : 6.0

Attack Vector LOCAL

Attack Complexity LOW

Privileges Required LOW

User Interaction REQUIRED

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact HIGH

Scope CHANGED

References

Link	Resource
https://docs.docker.com/desktop/release-notes/#4680	Release Notes

Configurations

Configuration 1 (hide)

AND

cpe:2.3:a:docker:docker_desktop:*:*:*:*:*:*:*:*

cpe:2.3:o:apple:macos:-:*:*:*:*:*:*:*

History

01 Jun 2026, 18:08

Type	Values Removed	Values Added
CPE		cpe:2.3:a:docker:docker_desktop:::::::: cpe:2.3:o:apple:macos:-:::::::*
References	~~() https://docs.docker.com/desktop/release-notes/#4680 -~~	() https://docs.docker.com/desktop/release-notes/#4680 - Release Notes
First Time		Docker Apple Docker docker Desktop Apple macos

22 May 2026, 20:44

Type	Values Removed	Values Added
New CVE

Information

Published : 2026-05-22 20:16

Updated : 2026-06-01 18:08

NVD link : CVE-2026-5817

Mitre link : CVE-2026-5817

CVE.ORG link : CVE-2026-5817

JSON object : View

Products Affected

docker

docker_desktop

apple

macos

CWE

CWE-829

Inclusion of Functionality from Untrusted Control Sphere

{"id": "CVE-2026-5817", "cveTags": [], "metrics": {"cvssMetricV31": [{"type": "Secondary", "source": "security@docker.com", "cvssData": {"scope": "CHANGED", "version": "3.1", "baseScore": 8.2, "attackVector": "LOCAL", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "REQUIRED", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "LOW", "confidentialityImpact": "HIGH"}, "impactScore": 6.0, "exploitabilityScore": 1.5}, {"type": "Primary", "source": "nvd@nist.gov", "cvssData": {"scope": "CHANGED", "version": "3.1", "baseScore": 8.6, "attackVector": "LOCAL", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "REQUIRED", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 6.0, "exploitabilityScore": 1.8}], "cvssMetricV40": [{"type": "Secondary", "source": "security@docker.com", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 8.8, "Automatable": "NOT_DEFINED", "attackVector": "LOCAL", "baseSeverity": "HIGH", "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/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", "exploitMaturity": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "userInteraction": "NONE", "attackComplexity": "LOW", "attackRequirements": "PRESENT", "privilegesRequired": "LOW", "subIntegrityImpact": "HIGH", "vulnIntegrityImpact": "HIGH", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "HIGH", "vulnAvailabilityImpact": "HIGH", "availabilityRequirement": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "subConfidentialityImpact": "HIGH", "vulnConfidentialityImpact": "HIGH", "confidentialityRequirement": "NOT_DEFINED", "modifiedAttackRequirements": "NOT_DEFINED", "modifiedPrivilegesRequired": "NOT_DEFINED", "modifiedSubIntegrityImpact": "NOT_DEFINED", "modifiedVulnIntegrityImpact": "NOT_DEFINED", "vulnerabilityResponseEffort": "NOT_DEFINED", "modifiedSubAvailabilityImpact": "NOT_DEFINED", "modifiedVulnAvailabilityImpact": "NOT_DEFINED", "modifiedSubConfidentialityImpact": "NOT_DEFINED", "modifiedVulnConfidentialityImpact": "NOT_DEFINED"}}]}, "published": "2026-05-22T20:16:35.120", "references": [{"url": "https://docs.docker.com/desktop/release-notes/#4680", "tags": ["Release Notes"], "source": "security@docker.com"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Secondary", "source": "security@docker.com", "description": [{"lang": "en", "value": "CWE-829"}]}], "descriptions": [{"lang": "en", "value": "The vllm-metal inference backend in Docker Model Runner on macOS unconditionally sets trust_remote_code=True when loading model tokenizers, and runs without sandboxing. This causes transformers.AutoTokenizer.from_pretrained() to import and execute arbitrary Python files included in any model pulled from an OCI registry, resulting in arbitrary code execution on the Docker host as the Docker Desktop user when inference is triggered.\n\nAny container on the Docker network can trigger this by calling the model-runner.docker.internal API to pull a malicious model and request inference."}], "lastModified": "2026-06-01T18:08:14.170", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:docker:docker_desktop:*:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "D13BBDD8-AB90-414E-A29B-75FA2125E68F", "versionEndExcluding": "4.68.0", "versionStartIncluding": "4.62.0"}], "operator": "OR"}, {"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:o:apple:macos:-:*:*:*:*:*:*:*", "vulnerable": false, "matchCriteriaId": "387021A0-AF36-463C-A605-32EA7DAC172E"}], "operator": "OR"}], "operator": "AND"}], "sourceIdentifier": "security@docker.com"}