CVE-2026-43632

llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/count_tokens) that bypass the task queue and access ctx_server.vocab directly on HTTP worker threads. Attackers can exploit a time-of-check-time-of-use race condition where the main thread destroys and frees vocab after the synchronization lock is released but before the handler finishes using it, causing a crash or potential code execution when --sleep-idle-seconds is configured.

CVSS v3 8.1 HIGH

8.1^/10

CVSS v3 : HIGH

Vector :

Exploitability : 2.2 / Impact : 5.9

Attack Vector NETWORK

Attack Complexity HIGH

Privileges Required NONE

User Interaction NONE

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact HIGH

Scope UNCHANGED

References

Link	Resource
https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches
https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tokenization-endpoints

Configurations

No configuration.

History

No history.

Information

Published : 2026-08-06 22:17

Updated : 2026-08-31 20:31

NVD link : CVE-2026-43632

Mitre link : CVE-2026-43632

CVE.ORG link : CVE-2026-43632

JSON object : View

Products Affected

No product.

CWE

CWE-367

Time-of-check Time-of-use (TOCTOU) Race Condition

CWE-416

Use After Free

{"id": "CVE-2026-43632", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-43632", "role": "CISA Coordinator", "options": [{"exploitation": "none"}, {"automatable": "no"}, {"technicalImpact": "total"}], "version": "2.0.3", "timestamp": "2026-08-08T02:09:08.150856Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 8.1, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "NONE", "attackComplexity": "HIGH", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 5.9, "exploitabilityScore": 2.2}], "cvssMetricV40": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 9.2, "Automatable": "NOT_DEFINED", "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "valueDensity": "NOT_DEFINED", "vectorString": "CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/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:X/R:X/V:X/RE:X/U:X", "exploitMaturity": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "userInteraction": "NONE", "attackComplexity": "HIGH", "attackRequirements": "PRESENT", "privilegesRequired": "NONE", "subIntegrityImpact": "NONE", "vulnIntegrityImpact": "HIGH", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "NONE", "vulnAvailabilityImpact": "HIGH", "availabilityRequirement": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "subConfidentialityImpact": "NONE", "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"}}]}, "affected": [{"source": "disclosure@vulncheck.com", "affectedData": [{"vendor": "ggml-org", "product": "llama.cpp", "versions": [{"status": "affected", "version": "b7492", "versionType": "custom", "lessThanOrEqual": "b9060"}], "defaultStatus": "affected"}]}], "published": "2026-08-06T22:17:06.343", "references": [{"url": "https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches", "source": "disclosure@vulncheck.com"}, {"url": "https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tokenization-endpoints", "source": "disclosure@vulncheck.com"}], "vulnStatus": "Undergoing Analysis", "weaknesses": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "description": [{"lang": "en", "value": "CWE-367"}, {"lang": "en", "value": "CWE-416"}]}], "descriptions": [{"lang": "en", "value": "llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/count_tokens) that bypass the task queue and access ctx_server.vocab directly on HTTP worker threads. Attackers can exploit a time-of-check-time-of-use race condition where the main thread destroys and frees vocab after the synchronization lock is released but before the handler finishes using it, causing a crash or potential code execution when --sleep-idle-seconds is configured."}], "lastModified": "2026-08-31T20:31:19.777", "sourceIdentifier": "disclosure@vulncheck.com"}