{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-85670", "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10", "state": "PUBLISHED", "assignerShortName": "VulnCheck", "dateReserved": "2026-09-04T13:32:36.617Z", "datePublished": "2026-09-04T14:32:25.391Z", "dateUpdated": "2026-09-04T14:32:25.391Z"}, "containers": {"cna": {"providerMetadata": {"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10", "shortName": "VulnCheck", "dateUpdated": "2026-09-04T14:32:25.391Z"}, "datePublic": "2026-06-10T00:00:00.000Z", "title": "tokenizers BpeBuilder Buffer Overflow via merge token", "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."}], "problemTypes": [{"descriptions": [{"lang": "en", "description": "Out-of-bounds Write", "cweId": "CWE-787", "type": "CWE"}]}], "affected": [{"vendor": "huggingface", "product": "tokenizers", "defaultStatus": "unaffected", "versions": [{"version": "0", "lessThanOrEqual": "0.23.2", "status": "affected", "versionType": "semver"}], "packageURL": "pkg:pypi/tokenizers"}], "metrics": [{"format": "CVSS", "cvssV4_0": {"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", "attackVector": "NETWORK", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "NONE", "userInteraction": "PASSIVE", "vulnConfidentialityImpact": "NONE", "vulnIntegrityImpact": "NONE", "vulnAvailabilityImpact": "HIGH", "subConfidentialityImpact": "NONE", "subIntegrityImpact": "NONE", "subAvailabilityImpact": "NONE", "baseScore": 7.1, "baseSeverity": "HIGH"}}, {"format": "CVSS", "cvssV3_1": {"version": "3.1", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H", "attackVector": "NETWORK", "attackComplexity": "LOW", "privilegesRequired": "NONE", "userInteraction": "REQUIRED", "scope": "UNCHANGED", "confidentialityImpact": "NONE", "integrityImpact": "NONE", "availabilityImpact": "HIGH", "baseScore": 6.5, "baseSeverity": "MEDIUM"}}], "references": [{"url": "https://github.com/huggingface/tokenizers/issues/2094", "tags": ["issue-tracking"], "name": "GitHub Issue #2094"}, {"url": "https://github.com/huggingface/tokenizers", "tags": ["product"]}, {"url": "https://github.com/huggingface/tokenizers/blob/v0.23.2/tokenizers/src/models/bpe/model.rs", "tags": ["technical-description"]}, {"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"}], "credits": [{"lang": "en", "value": "George Chen", "type": "finder"}], "x_generator": {"engine": "vulncheck-endgame"}}}}

{}

{"affected": [{"affectedData": [{"defaultStatus": "unaffected", "packageURL": "pkg:pypi/tokenizers", "product": "tokenizers", "vendor": "huggingface", "versions": [{"lessThanOrEqual": "0.23.2", "status": "affected", "version": "0", "versionType": "semver"}]}], "source": "disclosure@vulncheck.com"}], "cveTags": [], "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."}], "id": "CVE-2026-85670", "lastModified": "2026-09-04T15:17:44.993", "metrics": {"cvssMetricV31": [{"cvssData": {"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"}, "exploitabilityScore": 2.8, "impactScore": 3.6, "source": "disclosure@vulncheck.com", "type": "Primary"}], "cvssMetricV40": [{"cvssData": {"Automatable": "NOT_DEFINED", "Recovery": "NOT_DEFINED", "Safety": "NOT_DEFINED", "attackComplexity": "LOW", "attackRequirements": "NONE", "attackVector": "NETWORK", "availabilityRequirement": "NOT_DEFINED", "baseScore": 7.1, "baseSeverity": "HIGH", "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": "PASSIVE", "valueDensity": "NOT_DEFINED", "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", "version": "4.0", "vulnAvailabilityImpact": "HIGH", "vulnConfidentialityImpact": "NONE", "vulnIntegrityImpact": "NONE", "vulnerabilityResponseEffort": "NOT_DEFINED"}, "source": "disclosure@vulncheck.com", "type": "Secondary"}]}, "published": "2026-09-04T15:17:44.993", "references": [{"source": "disclosure@vulncheck.com", "url": "https://github.com/huggingface/tokenizers"}, {"source": "disclosure@vulncheck.com", "url": "https://github.com/huggingface/tokenizers/blob/v0.23.2/tokenizers/src/models/bpe/model.rs"}, {"source": "disclosure@vulncheck.com", "url": "https://github.com/huggingface/tokenizers/issues/2094"}, {"source": "disclosure@vulncheck.com", "url": "https://www.vulncheck.com/advisories/tokenizers-bpebuilder-buffer-overflow-via-merge-token"}], "sourceIdentifier": "disclosure@vulncheck.com", "vulnStatus": "Received", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-787"}], "source": "disclosure@vulncheck.com", "type": "Primary"}]}

{}

{"affected": [{"configurations": [{"platform": null, "status": "affected", "versions": {"scheme": "semver", "value": "[0,0.23.2]"}}], "enrichment": {"confidence": 100.0, "confidence_source": "cna", "scores": [{"score": 100.0, "source": "cna"}]}, "original": {"product": "tokenizers", "source": "cna", "vendor": "huggingface"}, "product": "tokenizers", "vendor": "huggingface"}], "created": "2026-09-04T15:52:30.020972+00:00", "updated": "2026-09-04T16:30:06.525669+00:00", "vendors": ["huggingface", "huggingface$PRODUCT$tokenizers"]}