{"id":"CVE-2026-65915","aliases":["DEBIAN-CVE-2026-65915","EUVD-2026-64309","GHSA-72r2-7mfr-5xr9","GHSA-79ph-w9m5-4v5m","PYSEC-2026-3731","UBUNTU-CVE-2026-65915"],"status":"published","title":"NLTK before 3.10.0 Arbitrary File Read via FileSystemPathPointer","description":"NLTK versions before 3.10.0 contain a logic bug in FileSystemPathPointer.open() where the sandbox validation check compares a normalized path against itself, making the security check permanently inert. Attackers can pass file:// URLs to nltk.data.load() to read arbitrary files accessible to the process user, including credentials and configuration files.","severity":{"version":"4.0","score":7.1,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N","level":"high","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-11","score":0.0041,"percentile":0.3574,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":true},"cwes":["CWE-284"],"published":"2026-08-22T14:12:41Z","modified":"2026-10-28T02:31:12Z","fixes":[{"ecosystem":"PyPI","package":"nltk","fixed_in":["3.10.0"],"sources":["ghsa","osv"]},{"ecosystem":"Debian:14","package":"nltk","fixed_in":["3.10.0-1"],"sources":["osv"]}],"affected":[{"source":"ghsa","ecosystem":"PyPI","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"3.9.3"},{"fixed":"3.10.0"}]}]},{"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":"3.10.0"}]}],"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"]},{"source":"osv","ecosystem":"PyPI","package":"nltk","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.10.0"}]}],"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"]},{"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"}],"references":[{"url":"https://github.com/nltk/nltk/security/advisories/GHSA-72r2-7mfr-5xr9","tags":["vendor-advisory","exploit","Exploit","Vendor Advisory","advisory","web","evidence"]},{"url":"https://www.vulncheck.com/advisories/nltk-before-arbitrary-file-read-via-filesystempathpointer","tags":["third-party-advisory","Third Party Advisory","advisory","web","report"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-65915","tags":["advisory"]},{"url":"https://github.com/nltk/nltk/pull/3522","tags":["web"]},{"url":"https://github.com/nltk/nltk/commit/69db9911fdba914ceeaca7aec6e892d1b14586a9","tags":["web"]},{"url":"https://github.com/pypa/advisory-database/tree/main/vulns/nltk/PYSEC-2026-3731.yaml","tags":["web"]},{"url":"https://huntr.com/bounties/a510de7b-ffaf-4a83-9bf8-fa7e63f4bd2d","tags":["web"]},{"url":"https://github.com/advisories/GHSA-72r2-7mfr-5xr9"},{"url":"https://github.com/advisories/GHSA-79ph-w9m5-4v5m"},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/65xxx/CVE-2026-65915.json","tags":["advisory"]},{"url":"https://security-tracker.debian.org/tracker/CVE-2026-65915","tags":["advisory"]},{"url":"https://github.com/nltk/nltk","tags":["package"]},{"url":"https://ubuntu.com/security/CVE-2026-65915","tags":["report"]},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-65915","tags":["report"]},{"url":"https://github.com/nltk/nltk/security/advisories/ghsa-72r2-7mfr-5xr9","tags":["report"]},{"url":"https://security-tracker.debian.org/tracker/cve-2026-65915","tags":["report"]},{"url":"https://github.com/cveproject/cvelistv5/tree/main/cves/2026/65xxx/cve-2026-65915.json","tags":["report"]},{"url":"https://nvd.nist.gov/vuln/detail/cve-2026-65915","tags":["report"]}],"sources":{"cve":[{"id":"CVE-2026-65915","title":"NLTK before 3.10.0 Arbitrary File Read via FileSystemPathPointer","description":"NLTK versions before 3.10.0 contain a logic bug in FileSystemPathPointer.open() where the sandbox validation check compares a normalized path against itself, making the security check permanently inert. Attackers can pass file:// URLs to nltk.data.load() to read arbitrary files accessible to the process user, including credentials and configuration files.","status":"published","published":"2026-08-22T14:12:41.391Z","modified":"2026-08-24T19:20:52.747Z","cvss":[{"version":"4.0","score":7.1,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N","level":"high","assessor":"cna"},{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N","level":"medium","assessor":"cna"}],"cwes":["CWE-284"],"updated_at":"2026-11-02T13:37:13.934727Z"}],"euvd":[{"id":"EUVD-2026-64309","description":"NLTK versions before 3.10.0 contain a logic bug in FileSystemPathPointer.open() where the sandbox validation check compares a normalized path against itself, making the security check permanently inert. Attackers can pass file:// URLs to nltk.data.load() to read arbitrary files accessible to the process user, including credentials and configuration files.","status":"published","published":"2026-08-22T14:12:41Z","modified":"2026-08-24T19:20:52Z","cvss":[{"version":"4.0","score":7.1,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N","level":"high"}],"updated_at":"2026-11-02T18:01:34.230875Z"}],"ghsa":[{"id":"GHSA-72r2-7mfr-5xr9","title":"NLTK: FileSystemPathPointer.open() sandbox check is dead code — arbitrary file read via file:// protocol","description":"### Summary\n\nThere's a logic bug in `FileSystemPathPointer.open()` inside `nltk/data.py`\nthat makes the sandbox check permanently inert. The guard condition is always\n`False` — meaning any file the process can read is accessible by passing a\n`file://` URL to `nltk.data.load()`.\n\n---\n\n### Details\n\nIn `nltk/data.py`, `FileSystemPathPointer.open()` was patched at some point\nwith a comment saying \"SECURITY PATCH ENFORCING SANDBOX\", but the check\ndoesn't work:\n```python\ndef open(self, encoding=None):\n    path = os.path.normpath(self._path)\n\n    # Block raw absolute reads such as \"/\" \"C:\\\\Windows\" etc.\n    if os.path.isabs(path) and path != os.path.normpath(self._path):\n        raise ValueError(f\"Direct absolute file access blocked: {path}\")\n\n    stream = open(self._path, \"rb\")\n```\n\n`path` is set to `os.path.normpath(self._path)` on line 1, then compared\nagainst `os.path.normpath(self._path)` again in the condition. They are\nalways equal. The `ValueError` never fires.\n\nOn top of that, `__init__` already calls `os.path.abspath()` before storing\n`self._path`, so it's normalized before `open()` is even called. Running\n`normpath` on it again changes nothing.\n\nThe `stream = open(self._path, \"rb\")` line is always reached regardless of\nwhat path was passed in.\n\n---\n\n### PoC\n\nTested on Python 3.11, NLTK 3.9.1, Ubuntu 22.04.\n```python\nimport nltk\nfrom nltk.data import FileSystemPathPointer\n\n# direct construction\nptr = FileSystemPathPointer(\"/etc/passwd\")\nwith ptr.open() as f:\n    print(f.read(300))\n\n# via load() using file:// URL\ndata = nltk.data.load(\"file:///etc/passwd\", format=\"raw\")\nprint(data[:300])\n```\n\nBoth print file contents. No exception is raised.\n\n---\n\n### Impact\n\nAny app that lets users influence the string passed to `nltk.data.load()` or\n`nltk.data.find()` is exposed — web APIs, notebook servers, multi-tenant\npipelines. An attacker can read any file the process user has access to:\n`/etc/passwd`, `.env` files, private keys, `~/.aws/credentials`, etc.\n\n## Suggested Fix\n\n**File:** `nltk/data.py` — `FileSystemPathPointer.open()` (lines 378–390)\n\n### What's wrong\n\nLine 387 compares `normpath(self._path)` against itself — always equal,\nso the `ValueError` never fires. The check is dead code.\n`__init__` already calls `abspath()` on construction, so re-running\n`normpath` inside `open()` changes nothing either.\n\n---\n\n### Fix\n\nValidate against the actual list of permitted data directories instead:\n```python\ndef open(self, encoding=None):\n    import nltk.data as _d\n    allowed = [os.path.abspath(p) for p in _d.path if p]\n    if allowed and not any(\n        os.path.commonpath([self._path, r]) == r for r in allowed\n    ):\n        raise ValueError(\n            f\"Access outside nltk_data blocked: {self._path!r}\"\n        )\n    stream = open(self._path, \"rb\")\n    if encoding is not None:\n        stream = SeekableUnicodeStreamReader(stream, encoding)\n    return stream\n```\n\n---\n\n### Why `commonpath` not `startswith`\n\n`startswith` is bypassable by a path that shares a prefix:\n```\n/tmp/nltk_data_evil\".startswith(\"/tmp/nltk_data\") → True  ✗\ncommonpath([\"/tmp/nltk_data_evil\", \"/tmp/nltk_data\"]) → \"/tmp\"  ✓\n```\n\n---\n\n### Diff\n```diff\n-    path = os.path.normpath(self._path)\n-    if os.path.isabs(path) and path != os.path.normpath(self._path):\n-        raise ValueError(f\"Direct absolute file access blocked: {path}\")\n-\n+    import nltk.data as _d\n+    allowed = [os.path.abspath(p) for p in _d.path if p]\n+    if allowed and not any(\n+        os.path.commonpath([self._path, r]) == r for r in allowed\n+    ):\n+        raise ValueError(f\"Access outside nltk_data blocked: {self._path!r}\")\n     stream = open(self._path, \"rb\")\n```","status":"published","published":"2026-09-08T15:27:12Z","modified":"2026-09-08T15:27:12Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N","level":"medium"}],"cwes":["CWE-284"],"updated_at":"2026-11-02T14:41:13.477974Z"},{"id":"GHSA-79ph-w9m5-4v5m","title":"Duplicate Advisory: FileSystemPathPointer.open() sandbox check is dead code — arbitrary file read via file:// protocol","description":"## Duplicate Advisory\n\nThis advisory has been withdrawn because it is a duplicate of GHSA-72r2-7mfr-5xr9. This link is maintained to preserve external references.\n\n## Original Description\nNLTK versions before 3.10.0 contain a logic bug in FileSystemPathPointer.open() where the sandbox validation check compares a normalized path against itself, making the security check permanently inert. Attackers can pass file:// URLs to nltk.data.load() to read arbitrary files accessible to the process user, including credentials and configuration files.","status":"withdrawn","published":"2026-08-22T15:31:03Z","modified":"2026-09-02T14:47:46Z","cvss":[{"version":"4.0","score":7.1,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/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":"high"},{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N","level":"medium"}],"cwes":["CWE-284"],"updated_at":"2026-11-02T14:41:10.121131Z"}],"nvd":[{"id":"CVE-2026-65915","description":"NLTK versions before 3.10.0 contain a logic bug in FileSystemPathPointer.open() where the sandbox validation check compares a normalized path against itself, making the security check permanently inert. Attackers can pass file:// URLs to nltk.data.load() to read arbitrary files accessible to the process user, including credentials and configuration files.","status":"published","published":"2026-08-22T15:16:19.5Z","modified":"2026-10-14T13:10:00.187Z","cvss":[{"version":"4.0","score":7.1,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/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":"high","assessor":"secondary"},{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N","level":"medium","assessor":"secondary"}],"cwes":["CWE-284"],"updated_at":"2026-11-02T14:12:40.665005Z"}],"osv":[{"id":"CVE-2026-65915","title":"NLTK before 3.10.0 Arbitrary File Read via FileSystemPathPointer","description":"NLTK versions before 3.10.0 contain a logic bug in FileSystemPathPointer.open() where the sandbox validation check compares a normalized path against itself, making the security check permanently inert. Attackers can pass file:// URLs to nltk.data.load() to read arbitrary files accessible to the process user, including credentials and configuration files.","status":"published","published":"2026-08-22T14:12:41.391Z","modified":"2026-10-28T02:31:12.517122186Z","cvss":[{"version":"4.0","score":7.1,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N","level":"high"}],"cwes":["CWE-284"],"updated_at":"2026-11-02T15:45:14.46177Z"},{"id":"DEBIAN-CVE-2026-65915","description":"NLTK versions before 3.10.0 contain a logic bug in FileSystemPathPointer.open() where the sandbox validation check compares a normalized path against itself, making the security check permanently inert. Attackers can pass file:// URLs to nltk.data.load() to read arbitrary files accessible to the process user, including credentials and configuration files.","status":"published","published":"2026-08-22T15:16:19.5Z","modified":"2026-10-15T09:47:44.905779535Z","cvss":[{"version":"4.0","score":7.1,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/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":"high"}],"updated_at":"2026-11-02T15:45:58.699079Z"},{"id":"GHSA-72r2-7mfr-5xr9","title":"NLTK: FileSystemPathPointer.open() sandbox check is dead code — arbitrary file read via file:// protocol","description":"### Summary\n\nThere's a logic bug in `FileSystemPathPointer.open()` inside `nltk/data.py`\nthat makes the sandbox check permanently inert. The guard condition is always\n`False` — meaning any file the process can read is accessible by passing a\n`file://` URL to `nltk.data.load()`.\n\n---\n\n### Details\n\nIn `nltk/data.py`, `FileSystemPathPointer.open()` was patched at some point\nwith a comment saying \"SECURITY PATCH ENFORCING SANDBOX\", but the check\ndoesn't work:\n```python\ndef open(self, encoding=None):\n    path = os.path.normpath(self._path)\n\n    # Block raw absolute reads such as \"/\" \"C:\\\\Windows\" etc.\n    if os.path.isabs(path) and path != os.path.normpath(self._path):\n        raise ValueError(f\"Direct absolute file access blocked: {path}\")\n\n    stream = open(self._path, \"rb\")\n```\n\n`path` is set to `os.path.normpath(self._path)` on line 1, then compared\nagainst `os.path.normpath(self._path)` again in the condition. They are\nalways equal. The `ValueError` never fires.\n\nOn top of that, `__init__` already calls `os.path.abspath()` before storing\n`self._path`, so it's normalized before `open()` is even called. Running\n`normpath` on it again changes nothing.\n\nThe `stream = open(self._path, \"rb\")` line is always reached regardless of\nwhat path was passed in.\n\n---\n\n### PoC\n\nTested on Python 3.11, NLTK 3.9.1, Ubuntu 22.04.\n```python\nimport nltk\nfrom nltk.data import FileSystemPathPointer\n\n# direct construction\nptr = FileSystemPathPointer(\"/etc/passwd\")\nwith ptr.open() as f:\n    print(f.read(300))\n\n# via load() using file:// URL\ndata = nltk.data.load(\"file:///etc/passwd\", format=\"raw\")\nprint(data[:300])\n```\n\nBoth print file contents. No exception is raised.\n\n---\n\n### Impact\n\nAny app that lets users influence the string passed to `nltk.data.load()` or\n`nltk.data.find()` is exposed — web APIs, notebook servers, multi-tenant\npipelines. An attacker can read any file the process user has access to:\n`/etc/passwd`, `.env` files, private keys, `~/.aws/credentials`, etc.\n\n## Suggested Fix\n\n**File:** `nltk/data.py` — `FileSystemPathPointer.open()` (lines 378–390)\n\n### What's wrong\n\nLine 387 compares `normpath(self._path)` against itself — always equal,\nso the `ValueError` never fires. The check is dead code.\n`__init__` already calls `abspath()` on construction, so re-running\n`normpath` inside `open()` changes nothing either.\n\n---\n\n### Fix\n\nValidate against the actual list of permitted data directories instead:\n```python\ndef open(self, encoding=None):\n    import nltk.data as _d\n    allowed = [os.path.abspath(p) for p in _d.path if p]\n    if allowed and not any(\n        os.path.commonpath([self._path, r]) == r for r in allowed\n    ):\n        raise ValueError(\n            f\"Access outside nltk_data blocked: {self._path!r}\"\n        )\n    stream = open(self._path, \"rb\")\n    if encoding is not None:\n        stream = SeekableUnicodeStreamReader(stream, encoding)\n    return stream\n```\n\n---\n\n### Why `commonpath` not `startswith`\n\n`startswith` is bypassable by a path that shares a prefix:\n```\n/tmp/nltk_data_evil\".startswith(\"/tmp/nltk_data\") → True  ✗\ncommonpath([\"/tmp/nltk_data_evil\", \"/tmp/nltk_data\"]) → \"/tmp\"  ✓\n```\n\n---\n\n### Diff\n```diff\n-    path = os.path.normpath(self._path)\n-    if os.path.isabs(path) and path != os.path.normpath(self._path):\n-        raise ValueError(f\"Direct absolute file access blocked: {path}\")\n-\n+    import nltk.data as _d\n+    allowed = [os.path.abspath(p) for p in _d.path if p]\n+    if allowed and not any(\n+        os.path.commonpath([self._path, r]) == r for r in allowed\n+    ):\n+        raise ValueError(f\"Access outside nltk_data blocked: {self._path!r}\")\n     stream = open(self._path, \"rb\")\n```","status":"published","published":"2026-09-08T15:27:12Z","modified":"2026-09-08T15:46:56.329043767Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N","level":"medium"}],"cwes":["CWE-284"],"updated_at":"2026-11-02T15:46:40.308826Z"},{"id":"GHSA-79ph-w9m5-4v5m","title":"Duplicate Advisory: FileSystemPathPointer.open() sandbox check is dead code — arbitrary file read via file:// protocol","description":"## Duplicate Advisory\n\nThis advisory has been withdrawn because it is a duplicate of GHSA-72r2-7mfr-5xr9. This link is maintained to preserve external references.\n\n## Original Description\nNLTK versions before 3.10.0 contain a logic bug in FileSystemPathPointer.open() where the sandbox validation check compares a normalized path against itself, making the security check permanently inert. Attackers can pass file:// URLs to nltk.data.load() to read arbitrary files accessible to the process user, including credentials and configuration files.","status":"withdrawn","published":"2026-08-22T15:31:03Z","modified":"2026-09-02T15:00:10.489493026Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N","level":"medium"},{"version":"4.0","score":7.1,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/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":"high"}],"cwes":["CWE-284"],"updated_at":"2026-11-02T15:46:41.002603Z"},{"id":"PYSEC-2026-3731","description":"NLTK versions before 3.10.0 contain a logic bug in FileSystemPathPointer.open() where the sandbox validation check compares a normalized path against itself, making the security check permanently inert. Attackers can pass file:// URLs to nltk.data.load() to read arbitrary files accessible to the process user, including credentials and configuration files.","status":"published","published":"2026-08-22T15:16:19.5Z","modified":"2026-09-01T09:15:03.471501849Z","cvss":[{"version":"4.0","score":7.1,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/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":"high"}],"updated_at":"2026-11-02T15:52:57.255153Z"},{"id":"UBUNTU-CVE-2026-65915","description":"NLTK versions before 3.10.0 contain a logic bug in FileSystemPathPointer.open() where the sandbox validation check compares a normalized path against itself, making the security check permanently inert. Attackers can pass file:// URLs to nltk.data.load() to read arbitrary files accessible to the process user, including credentials and configuration files.","status":"published","published":"2026-08-22T15:16:00Z","modified":"2026-10-17T12:59:17.804243863Z","cvss":[{"version":"4.0","score":7.1,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N","level":"high"},{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N","level":"medium"},{"version":"4.0","score":7.1,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N","level":"high"},{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N","level":"medium"}],"updated_at":"2026-11-02T16:56:53.710209Z"}]}}