{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-43632", "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10", "state": "PUBLISHED", "assignerShortName": "VulnCheck", "dateReserved": "2026-05-01T18:22:45.641Z", "datePublished": "2026-08-06T15:53:19.379Z", "dateUpdated": "2026-08-14T16:49:56.563Z"}, "containers": {"cna": {"providerMetadata": {"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10", "shortName": "VulnCheck", "dateUpdated": "2026-08-14T16:49:56.563Z"}, "title": "llama.cpp b7492\u2013b9060 Use-After-Free in Tokenization Endpoints", "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."}], "tags": ["x_open-source"], "datePublic": "2026-05-06T00:00:00.000Z", "problemTypes": [{"descriptions": [{"lang": "en", "cweId": "CWE-416", "description": "Use After Free", "type": "CWE"}, {"lang": "en", "cweId": "CWE-367", "description": "Time-of-check Time-of-use (TOCTOU) Race Condition", "type": "CWE"}]}], "affected": [{"vendor": "ggml-org", "product": "llama.cpp", "versions": [{"status": "affected", "version": "b7492", "lessThanOrEqual": "b9060", "versionType": "custom"}], "defaultStatus": "affected"}], "cpeApplicability": [{"nodes": [{"operator": "OR", "negate": false, "cpeMatch": [{"vulnerable": true, "criteria": "cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*", "versionStartIncluding": "b7492", "versionEndIncluding": "b9060"}]}]}], "metrics": [{"format": "CVSS", "scenarios": [{"lang": "en", "value": "GENERAL"}], "cvssV4_0": {"attackVector": "NETWORK", "attackComplexity": "HIGH", "attackRequirements": "PRESENT", "privilegesRequired": "NONE", "userInteraction": "NONE", "vulnConfidentialityImpact": "HIGH", "subConfidentialityImpact": "NONE", "vulnIntegrityImpact": "HIGH", "subIntegrityImpact": "NONE", "vulnAvailabilityImpact": "HIGH", "subAvailabilityImpact": "NONE", "exploitMaturity": "NOT_DEFINED", "Safety": "NOT_DEFINED", "Automatable": "NOT_DEFINED", "Recovery": "NOT_DEFINED", "valueDensity": "NOT_DEFINED", "vulnerabilityResponseEffort": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "version": "4.0", "baseSeverity": "CRITICAL", "baseScore": 9.2, "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"}}, {"format": "CVSS", "scenarios": [{"lang": "en", "value": "GENERAL"}], "cvssV3_1": {"attackVector": "NETWORK", "attackComplexity": "HIGH", "privilegesRequired": "NONE", "userInteraction": "NONE", "scope": "UNCHANGED", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "availabilityImpact": "HIGH", "version": "3.1", "baseSeverity": "HIGH", "baseScore": 8.1, "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H"}}], "references": [{"url": "https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches", "tags": ["mitigation"]}, {"url": "https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tokenization-endpoints", "tags": ["third-party-advisory"]}], "credits": [{"lang": "en", "value": "Vladimir Tokarev (@G1ND1L4) - Vulnerability Research Tech Lead, Cyera", "type": "finder"}, {"lang": "en", "value": "Ofek Itach (@ofekitach) - Security Research Team Lead, Cyera", "type": "finder"}], "source": {"discovery": "EXTERNAL"}, "x_generator": {"engine": "vulncheck"}}, "adp": [{"metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2026-08-08T02:09:08.150856Z", "id": "CVE-2026-43632", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "total"}], "role": "CISA Coordinator", "version": "2.0.3"}}}], "title": "CISA ADP Vulnrichment", "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-08-08T02:09:18.676Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2026-43632", "role": "CISA Coordinator", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "total"}], "version": "2.0.3", "timestamp": "2026-08-08T02:09:08.150856Z"}}}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-08-08T02:09:14.121Z"}}], "cna": {"tags": ["x_open-source"], "title": "llama.cpp b7492\u2013b9060 Use-After-Free in Tokenization Endpoints", "source": {"discovery": "EXTERNAL"}, "credits": [{"lang": "en", "type": "finder", "value": "Vladimir Tokarev (@G1ND1L4) - Vulnerability Research Tech Lead, Cyera"}, {"lang": "en", "type": "finder", "value": "Ofek Itach (@ofekitach) - Security Research Team Lead, Cyera"}], "metrics": [{"format": "CVSS", "cvssV4_0": {"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", "exploitMaturity": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "userInteraction": "NONE", "attackComplexity": "HIGH", "attackRequirements": "PRESENT", "privilegesRequired": "NONE", "subIntegrityImpact": "NONE", "vulnIntegrityImpact": "HIGH", "subAvailabilityImpact": "NONE", "vulnAvailabilityImpact": "HIGH", "subConfidentialityImpact": "NONE", "vulnConfidentialityImpact": "HIGH", "vulnerabilityResponseEffort": "NOT_DEFINED"}, "scenarios": [{"lang": "en", "value": "GENERAL"}]}, {"format": "CVSS", "cvssV3_1": {"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"}, "scenarios": [{"lang": "en", "value": "GENERAL"}]}], "affected": [{"vendor": "ggml-org", "product": "llama.cpp", "versions": [{"status": "affected", "version": "b7492", "versionType": "custom", "lessThanOrEqual": "b9060"}], "defaultStatus": "affected"}], "datePublic": "2026-05-06T00:00:00.000Z", "references": [{"url": "https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches", "tags": ["mitigation"]}, {"url": "https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tokenization-endpoints", "tags": ["third-party-advisory"]}], "x_generator": {"engine": "vulncheck"}, "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."}], "problemTypes": [{"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-416", "description": "Use After Free"}, {"lang": "en", "type": "CWE", "cweId": "CWE-367", "description": "Time-of-check Time-of-use (TOCTOU) Race Condition"}]}], "cpeApplicability": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*", "vulnerable": true, "versionEndIncluding": "b9060", "versionStartIncluding": "b7492"}], "operator": "OR"}]}], "providerMetadata": {"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10", "shortName": "VulnCheck", "dateUpdated": "2026-08-14T16:49:56.563Z"}}}, "cveMetadata": {"cveId": "CVE-2026-43632", "state": "PUBLISHED", "dateUpdated": "2026-08-14T16:49:56.563Z", "dateReserved": "2026-05-01T18:22:45.641Z", "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10", "datePublished": "2026-08-06T15:53:19.379Z", "assignerShortName": "VulnCheck"}, "dataVersion": "5.2"}

{"affected": [{"affectedData": [{"defaultStatus": "affected", "product": "llama.cpp", "vendor": "ggml-org", "versions": [{"lessThanOrEqual": "b9060", "status": "affected", "version": "b7492", "versionType": "custom"}]}], "source": "[email protected]"}], "cveTags": [], "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."}], "id": "CVE-2026-43632", "lastModified": "2026-08-08T02:17:17.033", "metrics": {"cvssMetricV31": [{"cvssData": {"attackComplexity": "HIGH", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "baseScore": 8.1, "baseSeverity": "HIGH", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "privilegesRequired": "NONE", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H", "version": "3.1"}, "exploitabilityScore": 2.2, "impactScore": 5.9, "source": "[email protected]", "type": "Secondary"}], "cvssMetricV40": [{"cvssData": {"Automatable": "NOT_DEFINED", "Recovery": "NOT_DEFINED", "Safety": "NOT_DEFINED", "attackComplexity": "HIGH", "attackRequirements": "PRESENT", "attackVector": "NETWORK", "availabilityRequirement": "NOT_DEFINED", "baseScore": 9.2, "baseSeverity": "CRITICAL", "confidentialityRequirement": "NOT_DEFINED", "exploitMaturity": "NOT_DEFINED", "integrityRequirement": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "modifiedAttackRequirements": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "modifiedPrivilegesRequired": "NOT_DEFINED", "modifiedSubAvailabilityImpact": "NOT_DEFINED", "modifiedSubConfidentialityImpact": "NOT_DEFINED", "modifiedSubIntegrityImpact": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedVulnAvailabilityImpact": "NOT_DEFINED", "modifiedVulnConfidentialityImpact": "NOT_DEFINED", "modifiedVulnIntegrityImpact": "NOT_DEFINED", "privilegesRequired": "NONE", "providerUrgency": "NOT_DEFINED", "subAvailabilityImpact": "NONE", "subConfidentialityImpact": "NONE", "subIntegrityImpact": "NONE", "userInteraction": "NONE", "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", "version": "4.0", "vulnAvailabilityImpact": "HIGH", "vulnConfidentialityImpact": "HIGH", "vulnIntegrityImpact": "HIGH", "vulnerabilityResponseEffort": "NOT_DEFINED"}, "source": "[email protected]", "type": "Secondary"}], "ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-43632", "options": [{"exploitation": "none"}, {"automatable": "no"}, {"technicalImpact": "total"}], "role": "CISA Coordinator", "timestamp": "2026-08-08T02:09:08.150856Z", "version": "2.0.3"}}]}, "published": "2026-08-06T22:17:06.343", "references": [{"source": "[email protected]", "url": "https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches"}, {"source": "[email protected]", "url": "https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tokenization-endpoints"}], "sourceIdentifier": "[email protected]", "vulnStatus": "Received", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-367"}, {"lang": "en", "value": "CWE-416"}], "source": "[email protected]", "type": "Secondary"}]}

{"bugzilla": {"description": "llama.cpp: llama.cpp: Potential code execution via a race condition in tokenization endpoints", "id": "2512244", "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2512244"}, "csaw": false, "cvss3": {"cvss3_base_score": "8.1", "cvss3_scoring_vector": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H", "status": "draft"}, "cwe": "CWE-364", "details": ["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.", "A flaw was found in llama.cpp. A use-after-free vulnerability exists in the llama-server's tokenization endpoints. This flaw allows a remote attacker to exploit a time-of-check-time-of-use race condition, where memory is freed by the main thread before an HTTP worker thread finishes using it. Successful exploitation could lead to a system crash or potentially arbitrary code execution."], "mitigation": {"lang": "en:us", "value": "To mitigate this issue, avoid configuring the `llama-server` with the `--sleep-idle-seconds` option. Disabling this option prevents the specific race condition that leads to the use-after-free vulnerability. If `llama-server` is running as a service, a restart of the service will be required for the change to take effect."}, "name": "CVE-2026-43632", "public_date": "2026-08-06T15:53:19Z", "references": ["https://www.cve.org/CVERecord?id=CVE-2026-43632\nhttps://nvd.nist.gov/vuln/detail/CVE-2026-43632\nhttps://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches"], "statement": "A use-after-free vulnerability was discovered in the llama-server component of llama.cpp. The flaw exists across six tokenization endpoints (/tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/count_tokens) that bypass the main task queue and access ctx_server.vocab directly on worker threads. When the service is configured with the --sleep-idle-seconds option, an unauthenticated remote attacker can exploit a time-of-check-to-time-of-use (TOCTOU) race condition. This occurs when the main thread releases synchronization locks and destroys the vocabulary structure while an HTTP worker thread is still actively processing a request.\nAn unauthenticated remote attacker sending concurrent HTTP requests can trigger heap corruption, leading to a service crash (Denial of Service) or potential arbitrary code execution within the security context of the llama-server process. Because exploitation relies on tight timing windows during idle cleanup cycles and impact is contained within the process boundaries without inherent host privilege escalation or OS isolation bypass, this vulnerability has been rated with an Important severity. Due to these reasons, this vulnerability has been rated with an Important severity.", "threat_severity": "Important"}

{"affected": [{"configurations": [{"platform": null, "status": "affected", "versions": {"scheme": "generic", "value": "[b7492,b9060]"}}], "enrichment": {"confidence": 100.0, "confidence_source": "matching", "scores": [{"score": 100.0, "source": "matching"}]}, "original": {"product": "llama.cpp", "source": "cna", "vendor": "ggml-org"}, "product": "llama.cpp", "vendor": "ggml-org"}], "created": "2026-08-07T01:15:05.058958+00:00", "updated": "2026-08-13T15:00:04.243156+00:00", "vendors": ["ggml-org", "ggml-org$PRODUCT$llama.cpp"]}