{"id":"CVE-2026-12259","aliases":["DEBIAN-CVE-2026-12259","EUVD-2026-52226","GHSA-5wp5-5229-5g6q","GHSA-gf32-cmjh-8m9v","GHSA-pv39-qrfq-g8gc","PYSEC-2026-3729","PYSEC-2026-4318","UBUNTU-CVE-2026-12259"],"status":"published","title":"Improper Input Validation in nltk/nltk","description":"In nltk version 3.9.4, the `nltk.downloader.Downloader._download_package()` function writes downloaded package bytes to disk and may extract them before enforcing SHA-256 or MD5 checksum validation. This allows an attacker to tamper with the package response body for `info.url` through a compromised mirror, malicious proxy, or other source-substitution condition, leading to the installation of attacker-controlled package bytes. The vulnerability can result in malicious corpus or model content being trusted by downstream users or applications.","severity":{"version":"3.0","score":5.3,"vector":"CVSS:3.0/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:H/A:N","level":"medium","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-10","score":0.00101,"percentile":0.00901,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":true},"cwes":["CWE-494"],"published":"2026-08-03T07:09:35Z","modified":"2026-10-28T02:30:40Z","fixes":[{"ecosystem":"PyPI","package":"nltk","fixed_in":["3.9.3"],"sources":["ghsa"]}],"affected":[{"source":"ghsa","ecosystem":"PyPI","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"3.9.2"},{"fixed":"3.9.3"}]}]},{"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"}]}],"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":"PyPI","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.9.3"}]}],"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","3.9b1"],"bundled":2},{"source":"osv","ecosystem":"PyPI","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.9.3"}]}],"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","3.9b1"],"bundled":2},{"source":"osv","ecosystem":"PyPI","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"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","3.9.4","3.9b1"],"bundled":2},{"source":"osv","ecosystem":"Ubuntu:Pro:14.04:LTS","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"}]}],"versions":["2.0~b9-0ubuntu4","2.0~b9-0ubuntu4.1~esm2","2.0~b9-0ubuntu4.1~esm4","2.0~b9-0ubuntu4.1~esm5","2.0~b9-0ubuntu4.1~esm6"]},{"source":"osv","ecosystem":"Ubuntu:Pro:16.04:LTS","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"}]}],"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","3.1-1ubuntu0.1+esm4"]},{"source":"osv","ecosystem":"Ubuntu:Pro:18.04:LTS","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"}]}],"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","3.2.5-1ubuntu0.1+esm4"]},{"source":"osv","ecosystem":"Ubuntu:Pro:20.04:LTS","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"}]}],"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","3.4.5-2ubuntu0.1~esm4"]},{"source":"osv","ecosystem":"Ubuntu:Pro:22.04:LTS","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"}]}],"versions":["3.5-1","3.6.5-1","3.6.7-1","3.7-1","3.7-1ubuntu0.1~esm1","3.7-1ubuntu0.1~esm2"]},{"source":"osv","ecosystem":"Ubuntu:Pro:24.04:LTS","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"}]}],"versions":["3.8.1-1","3.8.1-1ubuntu0.1~esm1","3.8.1-1ubuntu0.1~esm2"]},{"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"}]}],"versions":["3.9.1-2","3.9.1-2build1","3.9.2-1","3.9.2-1ubuntu0.1~esm1","3.9.2-1ubuntu0.1~esm2"]}],"products":[{"vendor":"nltk","product":"nltk"},{"vendor":"nltk","product":"nltk/nltk"}],"references":[{"url":"https://huntr.com/bounties/659ccf6d-12d4-4d4a-84c0-078633c35a5d","tags":["Permissions Required","web","report"]},{"url":"https://github.com/nltk/nltk/security/advisories/GHSA-5wp5-5229-5g6q","tags":["advisory","web","evidence"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-12259","tags":["advisory"]},{"url":"https://github.com/nltk/nltk/pull/3449","tags":["web"]},{"url":"https://github.com/nltk/nltk/commit/0e26734a61094b628d93e26dc18dd7302567ac46","tags":["web"]},{"url":"https://github.com/nltk/nltk/releases/tag/3.9.3","tags":["web"]},{"url":"https://github.com/pypa/advisory-database/tree/main/vulns/nltk/PYSEC-2026-3729.yaml","tags":["web"]},{"url":"https://www.vulncheck.com/advisories/nltk-before-missing-post-download-integrity-verification","tags":["advisory","web"]},{"url":"https://github.com/advisories/GHSA-5wp5-5229-5g6q","tags":["advisory"]},{"url":"https://github.com/advisories/GHSA-pv39-qrfq-g8gc"},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/12xxx/CVE-2026-12259.json","tags":["advisory"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/63xxx/CVE-2026-63310.json","tags":["advisory"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-63310","tags":["advisory"]},{"url":"https://security-tracker.debian.org/tracker/CVE-2026-12259","tags":["advisory"]},{"url":"https://github.com/nltk/nltk","tags":["package"]},{"url":"https://ubuntu.com/security/CVE-2026-12259","tags":["report"]},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-12259","tags":["report"]}],"sources":{"cve":[{"id":"CVE-2026-12259","title":"Improper Input Validation in nltk/nltk","description":"In nltk version 3.9.4, the `nltk.downloader.Downloader._download_package()` function writes downloaded package bytes to disk and may extract them before enforcing SHA-256 or MD5 checksum validation. This allows an attacker to tamper with the package response body for `info.url` through a compromised mirror, malicious proxy, or other source-substitution condition, leading to the installation of attacker-controlled package bytes. The vulnerability can result in malicious corpus or model content being trusted by downstream users or applications.","status":"published","published":"2026-08-03T07:09:35.262Z","modified":"2026-08-03T14:59:01.815Z","cvss":[{"version":"3.0","score":5.3,"vector":"CVSS:3.0/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:H/A:N","level":"medium","assessor":"cna"}],"cwes":["CWE-494"],"updated_at":"2026-11-02T14:19:48.461833Z"}],"euvd":[{"id":"EUVD-2026-52226","description":"In nltk version 3.9.4, the `nltk.downloader.Downloader._download_package()` function writes downloaded package bytes to disk and may extract them before enforcing SHA-256 or MD5 checksum validation. This allows an attacker to tamper with the package response body for `info.url` through a compromised mirror, malicious proxy, or other source-substitution condition, leading to the installation of attacker-controlled package bytes. The vulnerability can result in malicious corpus or model content being trusted by downstream users or applications.","status":"published","published":"2026-08-03T07:09:35Z","modified":"2026-08-03T14:59:01Z","cvss":[{"version":"3.0","score":5.3,"vector":"CVSS:3.0/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:H/A:N","level":"medium"}],"updated_at":"2026-11-02T18:02:24.366648Z"}],"ghsa":[{"id":"GHSA-5wp5-5229-5g6q","title":"NLTK: Missing Post-Download Integrity Verification Allows Malicious Package Injection","description":"NLTK's package downloader in nltk/downloader.py does not verify file integrity after download and before extraction.\n\nThe download flow at lines 789-825:\n1. File is downloaded to a temp path via HTTP\n2. os.replace(tmp_filepath, filepath) moves it to the final location (line 799)\n3. Extraction begins via _unzip_iter() (line 825)\n\nBetween steps 2 and 3, there is no SHA-256 verification. The checksum logic exists in _pkg_status() (lines 982-1015) but it is only used BEFORE download as a status check (\"is this package already installed and up-to-date?\"). It is never called after download to verify the file that was actually received.\n\nAttack vectors:\n1. MITM during HTTP download (NLTK downloads from http:// by default on some mirrors)\n2. Race condition on shared filesystems (attacker replaces file between os.replace and _unzip_iter)\n3. DNS poisoning redirecting to attacker-controlled server\n\nPoC:\n```python\nimport nltk\nimport unittest.mock\nimport zipfile\nimport io\nimport os\n\n# Create a malicious zip that will be \"downloaded\"\nmalicious_zip = io.BytesIO()\nwith zipfile.ZipFile(malicious_zip, 'w') as zf:\n    zf.writestr('punkt_tab/tokenizers/punkt_tab/english.pickle', \n                b'MALICIOUS PAYLOAD - attacker controlled content')\n\n# Patch urllib to return our malicious zip\nwith unittest.mock.patch('urllib.request.urlopen') as mock_urlopen:\n    mock_response = unittest.mock.MagicMock()\n    mock_response.read.return_value = malicious_zip.getvalue()\n    mock_response.headers = {'Content-Length': str(len(malicious_zip.getvalue()))}\n    mock_urlopen.return_value = mock_response\n    \n    # Download proceeds, no integrity check catches the swap\n    # nltk.download('punkt_tab')  # Would install attacker payload\n```\n\nThis is distinct from CVE-2024-39705 (pickle deserialization via download) and CVE-2025-14009 (zip-slip path traversal). Those address what happens AFTER extraction. This finding addresses the gap BEFORE extraction where integrity is never verified.\n\nSuggested fix: After os.replace() and before _unzip_iter(), compute SHA-256 of the final file and compare against the expected checksum from the package index. Reject and delete the file if the hash does not match.","status":"published","published":"2026-09-08T15:27:55Z","modified":"2026-10-27T07:58:08Z","cvss":[{"version":"3.1","score":5.3,"vector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:H/A:N","level":"medium"}],"cwes":["CWE-494"],"updated_at":"2026-11-02T14:41:36.858527Z"},{"id":"GHSA-pv39-qrfq-g8gc","title":"Duplicate Advisory: NLTK: Missing Post-Download Integrity Verification Allows Malicious Package Injection","description":"## Duplicate Advisory\n\nThis advisory has been withdrawn because it is a duplicate of GHSA-5wp5-5229-5g6q. This link is maintained to preserve external references.\n\n## Original Description\nIn nltk version 3.9.4, the `nltk.downloader.Downloader._download_package()` function writes downloaded package bytes to disk and may extract them before enforcing SHA-256 or MD5 checksum validation. This allows an attacker to tamper with the package response body for `info.url` through a compromised mirror, malicious proxy, or other source-substitution condition, leading to the installation of attacker-controlled package bytes. The vulnerability can result in malicious corpus or model content being trusted by downstream users or applications.","status":"withdrawn","published":"2026-08-03T09:32:37Z","modified":"2026-09-01T20:30:35Z","cvss":[{"version":"3.0","score":5.3,"vector":"CVSS:3.0/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:H/A:N","level":"medium"}],"cwes":["CWE-494"],"updated_at":"2026-11-02T14:41:08.980668Z"}],"nvd":[{"id":"CVE-2026-12259","description":"In nltk version 3.9.4, the `nltk.downloader.Downloader._download_package()` function writes downloaded package bytes to disk and may extract them before enforcing SHA-256 or MD5 checksum validation. This allows an attacker to tamper with the package response body for `info.url` through a compromised mirror, malicious proxy, or other source-substitution condition, leading to the installation of attacker-controlled package bytes. The vulnerability can result in malicious corpus or model content being trusted by downstream users or applications.","status":"published","published":"2026-08-03T08:17:17.88Z","modified":"2026-10-23T22:10:00.16Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:N","level":"medium","assessor":"primary"},{"version":"3.0","score":5.3,"vector":"CVSS:3.0/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:H/A:N","level":"medium","assessor":"secondary"}],"cwes":["CWE-494"],"updated_at":"2026-11-02T14:12:34.290716Z"}],"osv":[{"id":"CVE-2026-12259","title":"Improper Input Validation in nltk/nltk","description":"In nltk version 3.9.4, the `nltk.downloader.Downloader._download_package()` function writes downloaded package bytes to disk and may extract them before enforcing SHA-256 or MD5 checksum validation. This allows an attacker to tamper with the package response body for `info.url` through a compromised mirror, malicious proxy, or other source-substitution condition, leading to the installation of attacker-controlled package bytes. The vulnerability can result in malicious corpus or model content being trusted by downstream users or applications.","status":"published","published":"2026-08-03T07:09:35.262Z","modified":"2026-10-28T02:30:40.339380773Z","cvss":[{"version":"3.0","score":5.3,"vector":"CVSS:3.0/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:H/A:N","level":"medium"}],"cwes":["CWE-494"],"updated_at":"2026-11-02T15:44:57.354194Z"},{"id":"CVE-2026-63310","title":"NLTK before 3.9.3 Missing Post-Download Integrity Verification","description":"NLTK before 3.9.3 fails to verify file integrity after downloading packages and before extraction in the downloader module. Attackers can perform man-in-the-middle attacks or DNS poisoning to inject malicious package contents that are extracted without validation.","status":"published","published":"2026-08-22T14:12:39.36Z","modified":"2026-10-16T10:56:05.808390648Z","cvss":[{"version":"4.0","score":9.3,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N","level":"critical"}],"cwes":["CWE-494"],"updated_at":"2026-11-02T15:45:13.306117Z"},{"id":"DEBIAN-CVE-2026-12259","description":"In nltk version 3.9.4, the `nltk.downloader.Downloader._download_package()` function writes downloaded package bytes to disk and may extract them before enforcing SHA-256 or MD5 checksum validation. This allows an attacker to tamper with the package response body for `info.url` through a compromised mirror, malicious proxy, or other source-substitution condition, leading to the installation of attacker-controlled package bytes. The vulnerability can result in malicious corpus or model content being trusted by downstream users or applications.","status":"published","published":"2026-08-03T08:17:17.88Z","modified":"2026-10-24T09:47:32.148329527Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:N","level":"medium"}],"updated_at":"2026-11-02T15:45:51.374409Z"},{"id":"GHSA-5wp5-5229-5g6q","title":"NLTK: Missing Post-Download Integrity Verification Allows Malicious Package Injection","description":"NLTK's package downloader in nltk/downloader.py does not verify file integrity after download and before extraction.\n\nThe download flow at lines 789-825:\n1. File is downloaded to a temp path via HTTP\n2. os.replace(tmp_filepath, filepath) moves it to the final location (line 799)\n3. Extraction begins via _unzip_iter() (line 825)\n\nBetween steps 2 and 3, there is no SHA-256 verification. The checksum logic exists in _pkg_status() (lines 982-1015) but it is only used BEFORE download as a status check (\"is this package already installed and up-to-date?\"). It is never called after download to verify the file that was actually received.\n\nAttack vectors:\n1. MITM during HTTP download (NLTK downloads from http:// by default on some mirrors)\n2. Race condition on shared filesystems (attacker replaces file between os.replace and _unzip_iter)\n3. DNS poisoning redirecting to attacker-controlled server\n\nPoC:\n```python\nimport nltk\nimport unittest.mock\nimport zipfile\nimport io\nimport os\n\n# Create a malicious zip that will be \"downloaded\"\nmalicious_zip = io.BytesIO()\nwith zipfile.ZipFile(malicious_zip, 'w') as zf:\n    zf.writestr('punkt_tab/tokenizers/punkt_tab/english.pickle', \n                b'MALICIOUS PAYLOAD - attacker controlled content')\n\n# Patch urllib to return our malicious zip\nwith unittest.mock.patch('urllib.request.urlopen') as mock_urlopen:\n    mock_response = unittest.mock.MagicMock()\n    mock_response.read.return_value = malicious_zip.getvalue()\n    mock_response.headers = {'Content-Length': str(len(malicious_zip.getvalue()))}\n    mock_urlopen.return_value = mock_response\n    \n    # Download proceeds, no integrity check catches the swap\n    # nltk.download('punkt_tab')  # Would install attacker payload\n```\n\nThis is distinct from CVE-2024-39705 (pickle deserialization via download) and CVE-2025-14009 (zip-slip path traversal). Those address what happens AFTER extraction. This finding addresses the gap BEFORE extraction where integrity is never verified.\n\nSuggested fix: After os.replace() and before _unzip_iter(), compute SHA-256 of the final file and compare against the expected checksum from the package index. Reject and delete the file if the hash does not match.","status":"published","published":"2026-09-08T15:27:55Z","modified":"2026-10-16T10:56:05.808390648Z","cvss":[{"version":"3.1","score":5.3,"vector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:H/A:N","level":"medium"}],"cwes":["CWE-494"],"updated_at":"2026-11-02T15:46:38.911014Z"},{"id":"GHSA-gf32-cmjh-8m9v","title":"Duplicate Advisory: NLTK: Missing Post-Download Integrity Verification Allows Malicious Package Injection","description":"## Duplicate Advisory\n\nThis advisory has been withdrawn because it is a duplicate of GHSA-5wp5-5229-5g6q. This link is maintained to preserve external references.\n\n## Original Description\nNLTK before 3.9.3 fails to verify file integrity after downloading packages and before extraction in the downloader module. Attackers can perform man-in-the-middle attacks or DNS poisoning to inject malicious package contents that are extracted without validation.","status":"withdrawn","published":"2026-08-22T15:31:03Z","modified":"2026-10-16T10:56:05.808390648Z","cvss":[{"version":"3.1","score":7.1,"vector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:H/A:H","level":"high"},{"version":"4.0","score":9.3,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/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","level":"critical"}],"cwes":["CWE-494"],"updated_at":"2026-11-02T15:46:47.822182Z"},{"id":"GHSA-pv39-qrfq-g8gc","title":"Duplicate Advisory: NLTK: Missing Post-Download Integrity Verification Allows Malicious Package Injection","description":"## Duplicate Advisory\n\nThis advisory has been withdrawn because it is a duplicate of GHSA-5wp5-5229-5g6q. This link is maintained to preserve external references.\n\n## Original Description\nIn nltk version 3.9.4, the `nltk.downloader.Downloader._download_package()` function writes downloaded package bytes to disk and may extract them before enforcing SHA-256 or MD5 checksum validation. This allows an attacker to tamper with the package response body for `info.url` through a compromised mirror, malicious proxy, or other source-substitution condition, leading to the installation of attacker-controlled package bytes. The vulnerability can result in malicious corpus or model content being trusted by downstream users or applications.","status":"withdrawn","published":"2026-08-03T09:32:37Z","modified":"2026-09-01T20:45:05.623447439Z","cvss":[{"version":"3.0","score":5.3,"vector":"CVSS:3.0/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:H/A:N","level":"medium"}],"cwes":["CWE-494"],"updated_at":"2026-11-02T15:46:53.700556Z"},{"id":"PYSEC-2026-3729","description":"NLTK before 3.9.3 fails to verify file integrity after downloading packages and before extraction in the downloader module. Attackers can perform man-in-the-middle attacks or DNS poisoning to inject malicious package contents that are extracted without validation.","status":"published","published":"2026-08-22T15:16:19.1Z","modified":"2026-10-16T10:56:05.808390648Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:H/A:N","level":"medium"}],"updated_at":"2026-11-02T15:52:57.255153Z"},{"id":"PYSEC-2026-4318","description":"In nltk version 3.9.4, the `nltk.downloader.Downloader._download_package()` function writes downloaded package bytes to disk and may extract them before enforcing SHA-256 or MD5 checksum validation. This allows an attacker to tamper with the package response body for `info.url` through a compromised mirror, malicious proxy, or other source-substitution condition, leading to the installation of attacker-controlled package bytes. The vulnerability can result in malicious corpus or model content being trusted by downstream users or applications.","status":"published","published":"2026-08-03T08:17:17.88Z","modified":"2026-10-16T10:56:05.808390648Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:N","level":"medium"}],"updated_at":"2026-11-02T15:52:57.671918Z"},{"id":"UBUNTU-CVE-2026-12259","description":"In nltk version 3.9.4, the `nltk.downloader.Downloader._download_package()` function writes downloaded package bytes to disk and may extract them before enforcing SHA-256 or MD5 checksum validation. This allows an attacker to tamper with the package response body for `info.url` through a compromised mirror, malicious proxy, or other source-substitution condition, leading to the installation of attacker-controlled package bytes. The vulnerability can result in malicious corpus or model content being trusted by downstream users or applications.","status":"published","published":"2026-08-03T08:17:00Z","modified":"2026-10-17T12:58:04.819175878Z","cvss":[{"version":"3.0","score":5.3,"vector":"CVSS:3.0/AV:N/AC:H/PR:N/UI:R/S:U/C:N/I:H/A:N","level":"medium"},{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:N","level":"medium"}],"updated_at":"2026-11-02T16:56:00.592716Z"}]}}