{
  "affected": [
    {
      "ranges": [
        {
          "database_specific": {
            "extracted_events": [
              {
                "introduced": "0"
              },
              {
                "fixed": "3.10.1"
              }
            ],
            "source": [
              "AFFECTED_FIELD",
              "REFERENCES"
            ]
          },
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "35813c85af3f13d4f7196085854eafb3d0c5db02"
            }
          ],
          "repo": "https://github.com/nltk/nltk",
          "type": "GIT"
        }
      ]
    }
  ],
  "database_specific": {
    "cna_assigner": "VulnCheck",
    "cwe_ids": [
      "CWE-1333"
    ],
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/72xxx/CVE-2026-72818.json"
  },
  "details": "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",
  "modified": "2026-08-23T03:42:46.409180706Z",
  "published": "2026-08-20T21:57:34.230Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://pypi.org"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/72xxx/CVE-2026-72818.json"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/nltk/nltk/releases/tag/v3.10.1"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-72818"
    },
    {
      "type": "ADVISORY",
      "url": "https://www.vulncheck.com/advisories/nltk-tweettokenizer-url-pattern-backtracks-catastrophically-on-naked-domain-like-input"
    },
    {
      "type": "REPORT",
      "url": "https://github.com/nltk/nltk/issues/3704"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/nltk/nltk"
    },
    {
      "type": "ARTICLE",
      "url": "https://github.com/nltk/nltk/blob/3.9.4/nltk/tokenize/casual.py"
    }
  ],
  "schema_version": "1.9.0",
  "severity": [
    {
      "score": "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",
      "type": "CVSS_V4"
    }
  ],
  "summary": "NLTK TweetTokenizer URL Pattern Backtracks Catastrophically on Naked-Domain-Like Input"
}