{
  "schemaVersion": 1,
  "attribution": [
    {
      "source": "CISA Known Exploited Vulnerabilities",
      "url": "https://www.cisa.gov/known-exploited-vulnerabilities-catalog",
      "licence": "US government work"
    },
    {
      "source": "GitHub Advisory Database",
      "url": "https://github.com/advisories",
      "licence": "CC BY 4.0"
    },
    {
      "source": "Have I Been Pwned",
      "url": "https://haveibeenpwned.com/",
      "licence": "CC BY 4.0"
    },
    {
      "source": "CVE Program (CVE records)",
      "url": "https://www.cve.org/Legal/TermsOfUse",
      "licence": "CVE Terms of Use",
      "notice": "Copyright © 1999-2026, The MITRE Corporation. CVE is a trademark and the CVE logo is a registered trademark of The MITRE Corporation.",
      "terms": "CVE Usage: MITRE hereby grants you a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare derivative works of, publicly display, publicly perform, sublicense, and distribute Common Vulnerabilities and Exposures (CVE™). Any copy you make for such purposes is authorized provided that you reproduce MITRE's copyright designation and this license in any such copy."
    },
    {
      "source": "FIRST EPSS",
      "url": "https://www.first.org/epss/",
      "licence": "free to use; FIRST requests attribution"
    }
  ],
  "record": {
    "id": "CVE-2026-72818",
    "sourceURL": "https://www.cve.org/CVERecord?id=CVE-2026-72818",
    "idYear": 2026,
    "status": "PUBLISHED",
    "publishedAt": "2026-08-20T21:57:34.230Z",
    "updatedAt": "2026-09-24T14:18:57.476Z",
    "importedAt": "2026-10-24T01:58:25.636Z",
    "snapshot": {
      "id": "cve_2026-10-24_midnight_baseline",
      "at": "2026-10-24T00:00:00.000Z",
      "source": "https://github.com/CVEProject/cvelistV5/releases/tag/cve_2026-10-24_0100Z"
    },
    "facts": {
      "title": "NLTK TweetTokenizer URL Pattern Backtracks Catastrophically on Naked-Domain-Like Input",
      "summary": "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.",
      "affected": [
        {
          "vendor": "nltk",
          "product": "nltk",
          "packageName": "nltk",
          "collectionURL": "https://pypi.org",
          "defaultStatus": "unaffected",
          "versions": [
            {
              "version": "0",
              "status": "affected",
              "versionType": "semver",
              "lessThan": "3.10.1"
            },
            {
              "version": "3.10.1",
              "status": "unaffected",
              "versionType": "semver"
            }
          ]
        }
      ]
    }
  }
}