{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-72818", "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10", "state": "PUBLISHED", "assignerShortName": "VulnCheck", "dateReserved": "2026-08-10T15:12:16.754Z", "datePublished": "2026-08-20T21:57:34.230Z", "dateUpdated": "2026-08-20T23:28:26.593Z"}, "containers": {"cna": {"providerMetadata": {"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10", "shortName": "VulnCheck", "dateUpdated": "2026-08-20T23:28:26.593Z"}, "datePublic": "2026-07-12T00:00:00.000Z", "title": "NLTK TweetTokenizer URL Pattern Backtracks Catastrophically on Naked-Domain-Like Input", "descriptions": [{"lang": "en", "value": "The URLS regular expression in nltk/tokenize/casual.py, compiled into TweetTokenizer.WORD_RE and applied by TweetTokenizer.tokenize, contains a naked-domain branch whose domain-label prefix [a-z0-9]+(?:[.\\-][a-z0-9]+)* is unbounded. Input consisting of many alternating label separators can be partitioned in exponentially many ways, and because the branch also requires a trailing top-level domain that such input never supplies, the engine explores those partitions before failing at each offset. A few kilobytes of input therefore consumes seconds to minutes of single-threaded CPU, and the HANG_RE substitution performed before matching does not collapse the pattern. TweetTokenizer is intended for tokenizing untrusted social-media text, so any service that applies it, or the module-level casual_tokenize, to submitted text can be stalled per request without authentication. Version 3.10.1 bounds the label repetition."}], "problemTypes": [{"descriptions": [{"lang": "en", "description": "Inefficient Regular Expression Complexity", "cweId": "CWE-1333", "type": "CWE"}]}], "affected": [{"vendor": "nltk", "product": "nltk", "defaultStatus": "unaffected", "packageURL": "pkg:pypi/nltk", "collectionURL": "https://pypi.org", "packageName": "nltk", "repo": "https://github.com/nltk/nltk", "versions": [{"version": "0", "lessThan": "3.10.1", "status": "affected", "versionType": "semver"}, {"version": "3.10.1", "status": "unaffected", "versionType": "semver"}], "programFiles": ["nltk/tokenize/casual.py"]}], "cpeApplicability": [{"nodes": [{"operator": "OR", "negate": false, "cpeMatch": [{"vulnerable": true, "criteria": "cpe:2.3:a:nltk:nltk:3.9.3:*:*:*:*:*:*:*"}, {"vulnerable": true, "criteria": "cpe:2.3:a:nltk:nltk:3.9.2:*:*:*:*:*:*:*"}, {"vulnerable": true, "criteria": "cpe:2.3:a:nltk:nltk:3.9.1:*:*:*:*:*:*:*"}, {"vulnerable": true, "criteria": "cpe:2.3:a:nltk:nltk:3.9:*:*:*:*:*:*:*"}, {"vulnerable": true, "criteria": "cpe:2.3:a:nltk:nltk:3.9:beta1:*:*:*:*:*:*"}, {"vulnerable": true, "criteria": "cpe:2.3:a:nltk:nltk:3.8.1:*:*:*:*:*:*:*"}, {"vulnerable": true, "criteria": "cpe:2.3:a:nltk:nltk:3.8:*:*:*:*:*:*:*"}, {"vulnerable": true, "criteria": "cpe:2.3:a:nltk:nltk:3.7:*:*:*:*:*:*:*"}, {"vulnerable": true, "criteria": "cpe:2.3:a:nltk:nltk:3.6.5:*:*:*:*:*:*:*"}, {"vulnerable": true, "criteria": "cpe:2.3:a:nltk:nltk:3.6.6:*:*:*:*:*:*:*"}, {"vulnerable": true, "criteria": "cpe:2.3:a:nltk:nltk:3.6.7:*:*:*:*:*:*:*"}]}]}], "metrics": [{"format": "CVSS", "cvssV4_0": {"version": "4.0", "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N", "attackVector": "NETWORK", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "NONE", "userInteraction": "NONE", "vulnConfidentialityImpact": "NONE", "vulnIntegrityImpact": "NONE", "vulnAvailabilityImpact": "HIGH", "subConfidentialityImpact": "NONE", "subIntegrityImpact": "NONE", "subAvailabilityImpact": "NONE", "baseScore": 8.7, "baseSeverity": "HIGH"}}, {"format": "CVSS", "cvssV3_1": {"version": "3.1", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H", "attackVector": "NETWORK", "attackComplexity": "LOW", "privilegesRequired": "NONE", "userInteraction": "NONE", "scope": "UNCHANGED", "confidentialityImpact": "NONE", "integrityImpact": "NONE", "availabilityImpact": "HIGH", "baseScore": 7.5, "baseSeverity": "HIGH"}}], "references": [{"url": "https://github.com/nltk/nltk/issues/3704", "tags": ["issue-tracking"], "name": "GitHub Issue #3704"}, {"url": "https://github.com/nltk/nltk/blob/3.9.4/nltk/tokenize/casual.py", "tags": ["technical-description"], "name": "Unbounded naked-domain branch in the URLS pattern at 3.9.4"}, {"url": "https://github.com/nltk/nltk/releases/tag/v3.10.1", "tags": ["release-notes"], "name": "NLTK v3.10.1"}, {"url": "https://github.com/nltk/nltk", "tags": ["product"]}, {"name": "VulnCheck Advisory: NLTK TweetTokenizer URL Pattern Backtracks Catastrophically on Naked-Domain-Like Input", "tags": ["third-party-advisory"], "url": "https://www.vulncheck.com/advisories/nltk-tweettokenizer-url-pattern-backtracks-catastrophically-on-naked-domain-like-input"}], "credits": [{"lang": "en", "value": "George Chen", "type": "reporter"}], "x_generator": {"engine": "vulncheck-endgame"}}}}

{}

{"affected": [{"affectedData": [{"collectionURL": "https://pypi.org", "defaultStatus": "unaffected", "packageName": "nltk", "packageURL": "pkg:pypi/nltk", "product": "nltk", "programFiles": ["nltk/tokenize/casual.py"], "repo": "https://github.com/nltk/nltk", "vendor": "nltk", "versions": [{"lessThan": "3.10.1", "status": "affected", "version": "0", "versionType": "semver"}, {"status": "unaffected", "version": "3.10.1", "versionType": "semver"}]}], "source": "[email protected]"}], "cveTags": [], "descriptions": [{"lang": "en", "value": "The URLS regular expression in nltk/tokenize/casual.py, compiled into TweetTokenizer.WORD_RE and applied by TweetTokenizer.tokenize, contains a naked-domain branch whose domain-label prefix [a-z0-9]+(?:[.\\-][a-z0-9]+)* is unbounded. Input consisting of many alternating label separators can be partitioned in exponentially many ways, and because the branch also requires a trailing top-level domain that such input never supplies, the engine explores those partitions before failing at each offset. A few kilobytes of input therefore consumes seconds to minutes of single-threaded CPU, and the HANG_RE substitution performed before matching does not collapse the pattern. TweetTokenizer is intended for tokenizing untrusted social-media text, so any service that applies it, or the module-level casual_tokenize, to submitted text can be stalled per request without authentication. Version 3.10.1 bounds the label repetition."}], "id": "CVE-2026-72818", "lastModified": "2026-08-20T22:18:05.087", "metrics": {"cvssMetricV31": [{"cvssData": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "baseScore": 7.5, "baseSeverity": "HIGH", "confidentialityImpact": "NONE", "integrityImpact": "NONE", "privilegesRequired": "NONE", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H", "version": "3.1"}, "exploitabilityScore": 3.9, "impactScore": 3.6, "source": "[email protected]", "type": "Primary"}], "cvssMetricV40": [{"cvssData": {"Automatable": "NOT_DEFINED", "Recovery": "NOT_DEFINED", "Safety": "NOT_DEFINED", "attackComplexity": "LOW", "attackRequirements": "NONE", "attackVector": "NETWORK", "availabilityRequirement": "NOT_DEFINED", "baseScore": 8.7, "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": "NONE", "valueDensity": "NOT_DEFINED", "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/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": "[email protected]", "type": "Secondary"}]}, "published": "2026-08-20T22:18:05.087", "references": [{"source": "[email protected]", "url": "https://github.com/nltk/nltk"}, {"source": "[email protected]", "url": "https://github.com/nltk/nltk/blob/3.9.4/nltk/tokenize/casual.py"}, {"source": "[email protected]", "url": "https://github.com/nltk/nltk/issues/3704"}, {"source": "[email protected]", "url": "https://github.com/nltk/nltk/releases/tag/v3.10.1"}, {"source": "[email protected]", "url": "https://www.vulncheck.com/advisories/nltk-tweettokenizer-url-pattern-backtracks-catastrophically-on-naked-domain-like-input"}], "sourceIdentifier": "[email protected]", "vulnStatus": "Received", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-1333"}], "source": "[email protected]", "type": "Primary"}]}

{}

{"affected": [{"configurations": [{"platform": null, "status": "affected", "versions": {"scheme": "semver", "value": "[0,3.10.1)"}}, {"platform": null, "status": "unaffected", "versions": {"scheme": "semver", "value": "3.10.1"}}], "enrichment": {"confidence": 95.0, "confidence_source": "inferred", "scores": [{"score": 95.0, "source": "inferred"}, {"score": 100.0, "source": "matching"}]}, "original": {"product": "nltk", "source": "cna", "vendor": "nltk"}, "product": "nltk", "vendor": "nltk"}], "created": "2026-08-21T00:45:07.118177+00:00", "updated": "2026-08-21T01:15:06.935375+00:00", "vendors": ["nltk", "nltk$PRODUCT$nltk"]}