{"api_version":"1","generated_at":"2026-09-05T19:37:14+00:00","cve":"CVE-2026-85670","urls":{"html":"https://cve.report/CVE-2026-85670","api":"https://cve.report/api/cve/CVE-2026-85670.json","docs":"https://cve.report/api","cve_org":"https://www.cve.org/CVERecord?id=CVE-2026-85670","nvd":"https://nvd.nist.gov/vuln/detail/CVE-2026-85670"},"summary":{"title":"tokenizers BpeBuilder Buffer Overflow via merge token","description":"tokenizers (Hugging Face) is affected by an out-of-bounds buffer access in BpeBuilder::build (tokenizers/src/models/bpe/model.rs). When loading a tokenizer.json via Tokenizer::from_file/from_str, the builder sizes a scratch buffer to the longest vocabulary key, then writes each concatenated merge rule into it. A merge whose concatenated token exceeds the longest vocabulary key overruns the buffer, which Rust turns into a panic that aborts the process in Rust and FFI embeddings. This occurs at load time with no encoding required, so an attacker who supplies a crafted tokenizer.json can cause a denial of service. A secondary defect at the same location can cause a usize underflow (panic in debug, potential memory corruption in release) when continuing_subword_prefix is set and a merge token is shorter than the prefix. Observed in version 0.23.1.","state":"PUBLISHED","assigner":"VulnCheck","published_at":"2026-09-04 15:17:44","updated_at":"2026-09-04 18:18:06"},"problem_types":["CWE-787","CWE-787 Out-of-bounds Write"],"metrics":[{"version":"4.0","source":"disclosure@vulncheck.com","type":"Secondary","score":"7.1","severity":"HIGH","vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:N/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","data":{"version":"4.0","vectorString":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:N/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","baseScore":7.1,"baseSeverity":"HIGH","attackVector":"NETWORK","attackComplexity":"LOW","attackRequirements":"NONE","privilegesRequired":"NONE","userInteraction":"PASSIVE","vulnConfidentialityImpact":"NONE","vulnIntegrityImpact":"NONE","vulnAvailabilityImpact":"HIGH","subConfidentialityImpact":"NONE","subIntegrityImpact":"NONE","subAvailabilityImpact":"NONE","exploitMaturity":"NOT_DEFINED","confidentialityRequirement":"NOT_DEFINED","integrityRequirement":"NOT_DEFINED","availabilityRequirement":"NOT_DEFINED","modifiedAttackVector":"NOT_DEFINED","modifiedAttackComplexity":"NOT_DEFINED","modifiedAttackRequirements":"NOT_DEFINED","modifiedPrivilegesRequired":"NOT_DEFINED","modifiedUserInteraction":"NOT_DEFINED","modifiedVulnConfidentialityImpact":"NOT_DEFINED","modifiedVulnIntegrityImpact":"NOT_DEFINED","modifiedVulnAvailabilityImpact":"NOT_DEFINED","modifiedSubConfidentialityImpact":"NOT_DEFINED","modifiedSubIntegrityImpact":"NOT_DEFINED","modifiedSubAvailabilityImpact":"NOT_DEFINED","Safety":"NOT_DEFINED","Automatable":"NOT_DEFINED","Recovery":"NOT_DEFINED","valueDensity":"NOT_DEFINED","vulnerabilityResponseEffort":"NOT_DEFINED","providerUrgency":"NOT_DEFINED"}},{"version":"4.0","source":"CNA","type":"CVSS","score":"7.1","severity":"HIGH","vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","data":{"attackComplexity":"LOW","attackRequirements":"NONE","attackVector":"NETWORK","baseScore":7.1,"baseSeverity":"HIGH","privilegesRequired":"NONE","subAvailabilityImpact":"NONE","subConfidentialityImpact":"NONE","subIntegrityImpact":"NONE","userInteraction":"PASSIVE","vectorString":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","version":"4.0","vulnAvailabilityImpact":"HIGH","vulnConfidentialityImpact":"NONE","vulnIntegrityImpact":"NONE"}},{"version":"3.1","source":"disclosure@vulncheck.com","type":"Secondary","score":"6.5","severity":"MEDIUM","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","data":{"version":"3.1","vectorString":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","baseScore":6.5,"baseSeverity":"MEDIUM","attackVector":"NETWORK","attackComplexity":"LOW","privilegesRequired":"NONE","userInteraction":"REQUIRED","scope":"UNCHANGED","confidentialityImpact":"NONE","integrityImpact":"NONE","availabilityImpact":"HIGH"}},{"version":"3.1","source":"CNA","type":"CVSS","score":"6.5","severity":"MEDIUM","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","data":{"attackComplexity":"LOW","attackVector":"NETWORK","availabilityImpact":"HIGH","baseScore":6.5,"baseSeverity":"MEDIUM","confidentialityImpact":"NONE","integrityImpact":"NONE","privilegesRequired":"NONE","scope":"UNCHANGED","userInteraction":"REQUIRED","vectorString":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","version":"3.1"}}],"references":[{"url":"https://github.com/huggingface/tokenizers","name":"https://github.com/huggingface/tokenizers","refsource":"disclosure@vulncheck.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://github.com/huggingface/tokenizers/issues/2094","name":"https://github.com/huggingface/tokenizers/issues/2094","refsource":"134c704f-9b21-4f2e-91b3-4a467353bcc0","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://github.com/huggingface/tokenizers/blob/v0.23.2/tokenizers/src/models/bpe/model.rs","name":"https://github.com/huggingface/tokenizers/blob/v0.23.2/tokenizers/src/models/bpe/model.rs","refsource":"disclosure@vulncheck.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://www.vulncheck.com/advisories/tokenizers-bpebuilder-buffer-overflow-via-merge-token","name":"https://www.vulncheck.com/advisories/tokenizers-bpebuilder-buffer-overflow-via-merge-token","refsource":"disclosure@vulncheck.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-85670","name":"CVE Program record","refsource":"CVE.ORG","tags":["canonical"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-85670","name":"NVD vulnerability detail","refsource":"NVD","tags":["canonical","analysis"]}],"affected":[{"source":"CNA","vendor":"huggingface","product":"tokenizers","version":"affected 0.23.2 semver","platforms":[]}],"timeline":[],"solutions":[],"workarounds":[],"exploits":[],"credits":[{"source":"CNA","value":"George Chen","lang":"en"}],"nvd_cpes":[],"vendor_comments":[],"enrichments":{"kev":null,"epss":null,"legacy_qids":[]},"source_records":{"cve_program":{"containers":{"adp":[{"metrics":[{"other":{"content":{"id":"CVE-2026-85670","options":[{"Exploitation":"poc"},{"Automatable":"no"},{"Technical Impact":"partial"}],"role":"CISA Coordinator","timestamp":"2026-09-04T17:49:21.636135Z","version":"2.0.3"},"type":"ssvc"}}],"providerMetadata":{"dateUpdated":"2026-09-04T17:49:42.263Z","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","shortName":"CISA-ADP"},"references":[{"tags":["exploit"],"url":"https://github.com/huggingface/tokenizers/issues/2094"}],"title":"CISA ADP Vulnrichment"}],"cna":{"affected":[{"defaultStatus":"unaffected","packageURL":"pkg:pypi/tokenizers","product":"tokenizers","vendor":"huggingface","versions":[{"lessThanOrEqual":"0.23.2","status":"affected","version":"0","versionType":"semver"}]}],"credits":[{"lang":"en","type":"finder","value":"George Chen"}],"datePublic":"2026-06-10T00:00:00.000Z","descriptions":[{"lang":"en","value":"tokenizers (Hugging Face) is affected by an out-of-bounds buffer access in BpeBuilder::build (tokenizers/src/models/bpe/model.rs). When loading a tokenizer.json via Tokenizer::from_file/from_str, the builder sizes a scratch buffer to the longest vocabulary key, then writes each concatenated merge rule into it. A merge whose concatenated token exceeds the longest vocabulary key overruns the buffer, which Rust turns into a panic that aborts the process in Rust and FFI embeddings. This occurs at load time with no encoding required, so an attacker who supplies a crafted tokenizer.json can cause a denial of service. A secondary defect at the same location can cause a usize underflow (panic in debug, potential memory corruption in release) when continuing_subword_prefix is set and a merge token is shorter than the prefix. Observed in version 0.23.1."}],"metrics":[{"cvssV4_0":{"attackComplexity":"LOW","attackRequirements":"NONE","attackVector":"NETWORK","baseScore":7.1,"baseSeverity":"HIGH","privilegesRequired":"NONE","subAvailabilityImpact":"NONE","subConfidentialityImpact":"NONE","subIntegrityImpact":"NONE","userInteraction":"PASSIVE","vectorString":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","version":"4.0","vulnAvailabilityImpact":"HIGH","vulnConfidentialityImpact":"NONE","vulnIntegrityImpact":"NONE"},"format":"CVSS"},{"cvssV3_1":{"attackComplexity":"LOW","attackVector":"NETWORK","availabilityImpact":"HIGH","baseScore":6.5,"baseSeverity":"MEDIUM","confidentialityImpact":"NONE","integrityImpact":"NONE","privilegesRequired":"NONE","scope":"UNCHANGED","userInteraction":"REQUIRED","vectorString":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","version":"3.1"},"format":"CVSS"}],"problemTypes":[{"descriptions":[{"cweId":"CWE-787","description":"Out-of-bounds Write","lang":"en","type":"CWE"}]}],"providerMetadata":{"dateUpdated":"2026-09-04T14:32:25.391Z","orgId":"83251b91-4cc7-4094-a5c7-464a1b83ea10","shortName":"VulnCheck"},"references":[{"name":"GitHub Issue #2094","tags":["issue-tracking"],"url":"https://github.com/huggingface/tokenizers/issues/2094"},{"tags":["product"],"url":"https://github.com/huggingface/tokenizers"},{"tags":["technical-description"],"url":"https://github.com/huggingface/tokenizers/blob/v0.23.2/tokenizers/src/models/bpe/model.rs"},{"name":"VulnCheck Advisory: tokenizers BpeBuilder Buffer Overflow via merge token","tags":["third-party-advisory"],"url":"https://www.vulncheck.com/advisories/tokenizers-bpebuilder-buffer-overflow-via-merge-token"}],"title":"tokenizers BpeBuilder Buffer Overflow via merge token","x_generator":{"engine":"vulncheck-endgame"}}},"cveMetadata":{"assignerOrgId":"83251b91-4cc7-4094-a5c7-464a1b83ea10","assignerShortName":"VulnCheck","cveId":"CVE-2026-85670","datePublished":"2026-09-04T14:32:25.391Z","dateReserved":"2026-09-04T13:32:36.617Z","dateUpdated":"2026-09-04T17:49:42.263Z","state":"PUBLISHED"},"dataType":"CVE_RECORD","dataVersion":"5.2"},"nvd":{"publishedDate":"2026-09-04 15:17:44","lastModifiedDate":"2026-09-04 18:18:06","problem_types":["CWE-787","CWE-787 Out-of-bounds Write"],"metrics":{"cvssMetricV40":[{"source":"disclosure@vulncheck.com","type":"Secondary","cvssData":{"version":"4.0","vectorString":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:N/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","baseScore":7.1,"baseSeverity":"HIGH","attackVector":"NETWORK","attackComplexity":"LOW","attackRequirements":"NONE","privilegesRequired":"NONE","userInteraction":"PASSIVE","vulnConfidentialityImpact":"NONE","vulnIntegrityImpact":"NONE","vulnAvailabilityImpact":"HIGH","subConfidentialityImpact":"NONE","subIntegrityImpact":"NONE","subAvailabilityImpact":"NONE","exploitMaturity":"NOT_DEFINED","confidentialityRequirement":"NOT_DEFINED","integrityRequirement":"NOT_DEFINED","availabilityRequirement":"NOT_DEFINED","modifiedAttackVector":"NOT_DEFINED","modifiedAttackComplexity":"NOT_DEFINED","modifiedAttackRequirements":"NOT_DEFINED","modifiedPrivilegesRequired":"NOT_DEFINED","modifiedUserInteraction":"NOT_DEFINED","modifiedVulnConfidentialityImpact":"NOT_DEFINED","modifiedVulnIntegrityImpact":"NOT_DEFINED","modifiedVulnAvailabilityImpact":"NOT_DEFINED","modifiedSubConfidentialityImpact":"NOT_DEFINED","modifiedSubIntegrityImpact":"NOT_DEFINED","modifiedSubAvailabilityImpact":"NOT_DEFINED","Safety":"NOT_DEFINED","Automatable":"NOT_DEFINED","Recovery":"NOT_DEFINED","valueDensity":"NOT_DEFINED","vulnerabilityResponseEffort":"NOT_DEFINED","providerUrgency":"NOT_DEFINED"}}],"cvssMetricV31":[{"source":"disclosure@vulncheck.com","type":"Secondary","cvssData":{"version":"3.1","vectorString":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","baseScore":6.5,"baseSeverity":"MEDIUM","attackVector":"NETWORK","attackComplexity":"LOW","privilegesRequired":"NONE","userInteraction":"REQUIRED","scope":"UNCHANGED","confidentialityImpact":"NONE","integrityImpact":"NONE","availabilityImpact":"HIGH"},"exploitabilityScore":2.8,"impactScore":3.6}],"ssvcV203":[{"source":"134c704f-9b21-4f2e-91b3-4a467353bcc0","ssvcData":{"timestamp":"2026-09-04T17:49:21.636135Z","id":"CVE-2026-85670","options":[{"exploitation":"poc"},{"automatable":"no"},{"technicalImpact":"partial"}],"role":"CISA Coordinator","version":"2.0.3"}}]},"configurations":[]},"legacy_mitre":{"record":{"CveYear":"2026","CveId":"85670","Ordinal":"1","Title":"tokenizers BpeBuilder Buffer Overflow via merge token","CVE":"CVE-2026-85670","Year":"2026"},"notes":[{"CveYear":"2026","CveId":"85670","Ordinal":"1","NoteData":"tokenizers (Hugging Face) is affected by an out-of-bounds buffer access in BpeBuilder::build (tokenizers/src/models/bpe/model.rs). When loading a tokenizer.json via Tokenizer::from_file/from_str, the builder sizes a scratch buffer to the longest vocabulary key, then writes each concatenated merge rule into it. A merge whose concatenated token exceeds the longest vocabulary key overruns the buffer, which Rust turns into a panic that aborts the process in Rust and FFI embeddings. This occurs at load time with no encoding required, so an attacker who supplies a crafted tokenizer.json can cause a denial of service. A secondary defect at the same location can cause a usize underflow (panic in debug, potential memory corruption in release) when continuing_subword_prefix is set and a merge token is shorter than the prefix. Observed in version 0.23.1.","Type":"Description","Title":"tokenizers BpeBuilder Buffer Overflow via merge token"}]}}}