[CVE-2024-9287] ensure that bracketed hosts found by urlsplit are of IPv6 or IPvFuture format

Fix urlparse incorrectly retrieves IPv4 and regular name hosts from inside of brackets

Reproducer is

    python3 -c \
    'from urllib.parse import urlparse; print(urlparse("https://user:some]password[@host.com"))'

This command should fail with the error "ValueError: '@host.com'
does not appear to be an IPv4 or IPv6 address". If it doesn’t and produces

    ParseResult(scheme='https', netloc='user:some]password[@host.com',
    path='', params='', query='', fragment='')

it is this bug.

Fixes: bsc#1233307 (CVE-2024-11168)
Fixes: gh#python#103848
Co-authored-by: JohnJamesUtley <[email protected]>
From-PR: gh#python/cpython!103849
Patch: CVE-2024-11168-validation-IPv6-addrs.patch

Author: mcepl

Lib/ipaddress.py

@@ -1886,12 +1886,32 @@ def max_prefixlen(self):
     def version(self):
         return self._version
 
+    @staticmethod
+    def _split_scope_id(ip_str):
+        """Helper function to parse IPv6 string address with scope id.
+
+        See RFC 4007 for details.
+
+        Args:
+            ip_str: A string, the IPv6 address.
+
+        Returns:
+            (addr, scope_id) tuple.
+
+        """
+        addr, sep, scope_id = ip_str.partition('%')
+        if not sep:
+            scope_id = None
+        elif not scope_id or '%' in scope_id:
+            raise AddressValueError('Invalid IPv6 address: "%r"' % ip_str)
+        return addr, scope_id
+
 
 class IPv6Address(_BaseV6, _BaseAddress):
 
     """Represent and manipulate single IPv6 Addresses."""
 
-    __slots__ = ('_ip', '__weakref__')
+    __slots__ = ('_ip', '_scope_id', '__weakref__')
 
     def __init__(self, address):
         """Instantiate a new IPv6 address object.
@@ -1914,19 +1934,23 @@ def __init__(self, address):
         if isinstance(address, int):
             self._check_int_address(address)
             self._ip = address
+            self._scope_id = None
             return
 
         # Constructing from a packed address
         if isinstance(address, bytes):
             self._check_packed_address(address, 16)
             self._ip = int.from_bytes(address, 'big')
+            self._scope_id = None
             return
 
         # Assume input argument to be string or any object representation
         # which converts into a formatted IP string.
         addr_str = str(address)
         if '/' in addr_str:
             raise AddressValueError("Unexpected '/' in %r" % address)
+        addr_str, self._scope_id = self._split_scope_id(addr_str)
+
         self._ip = self._ip_int_from_string(addr_str)
 
     @property

Lib/test/test_urlparse.py

@@ -1035,6 +1035,32 @@ def test_issue14072(self):
         self.assertEqual(p2.scheme, 'tel')
         self.assertEqual(p2.path, '+31641044153')
 
+    def test_invalid_bracketed_hosts(self):
+        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[192.0.2.146]/Path?Query')
+        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[important.com:8000]/Path?Query')
+        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[v123r.IP]/Path?Query')
+        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[v12ae]/Path?Query')
+        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[v.IP]/Path?Query')
+        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[v123.]/Path?Query')
+        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[v]/Path?Query')
+        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[0439:23af::2309::fae7:1234]/Path?Query')
+        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[0439:23af:2309::fae7:1234:2342:438e:192.0.2.146]/Path?Query')
+        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@]v6a.ip[/Path')
+
+    def test_splitting_bracketed_hosts(self):
+        p1 = urllib.parse.urlsplit('scheme://user@[v6a.ip]/path?query')
+        self.assertEqual(p1.hostname, 'v6a.ip')
+        self.assertEqual(p1.username, 'user')
+        self.assertEqual(p1.path, '/path')
+        p2 = urllib.parse.urlsplit('scheme://user@[0439:23af:2309::fae7%test]/path?query')
+        self.assertEqual(p2.hostname, '0439:23af:2309::fae7%test')
+        self.assertEqual(p2.username, 'user')
+        self.assertEqual(p2.path, '/path')
+        p3 = urllib.parse.urlsplit('scheme://user@[0439:23af:2309::fae7:1234:192.0.2.146%test]/path?query')
+        self.assertEqual(p3.hostname, '0439:23af:2309::fae7:1234:192.0.2.146%test')
+        self.assertEqual(p3.username, 'user')
+        self.assertEqual(p3.path, '/path')
+
     def test_telurl_params(self):
         p1 = urllib.parse.urlparse('tel:123-4;phone-context=+1-650-516')
         self.assertEqual(p1.scheme, 'tel')

Lib/urllib/parse.py

@@ -30,6 +30,7 @@
 import re
 import sys
 import collections
+import ipaddress
 
 __all__ = ["urlparse", "urlunparse", "urljoin", "urldefrag",
            "urlsplit", "urlunsplit", "urlencode", "parse_qs",
@@ -417,6 +418,17 @@ def _checknetloc(netloc):
             raise ValueError("netloc '" + netloc + "' contains invalid " +
                              "characters under NFKC normalization")
 
+# Valid bracketed hosts are defined in
+# https://www.rfc-editor.org/rfc/rfc3986#page-49 and https://url.spec.whatwg.org/
+def _check_bracketed_host(hostname):
+    if hostname.startswith('v'):
+        if not re.match(r"\Av[a-fA-F0-9]+\..+\Z", hostname):
+            raise ValueError(f"IPvFuture address is invalid")
+    else:
+        ip = ipaddress.ip_address(hostname) # Throws Value Error if not IPv6 or IPv4
+        if isinstance(ip, ipaddress.IPv4Address):
+            raise ValueError(f"An IPv4 address cannot be in brackets")
+
 def _remove_unsafe_bytes_from_url(url):
     for b in _UNSAFE_URL_BYTES_TO_REMOVE:
         url = url.replace(b, "")
@@ -467,12 +479,14 @@ def urlsplit(url, scheme='', allow_fragments=True):
             if not rest or any(c not in '0123456789' for c in rest):
                 # not a port number
                 scheme, url = url[:i].lower(), rest
-
     if url[:2] == '//':
         netloc, url = _splitnetloc(url, 2)
         if (('[' in netloc and ']' not in netloc) or
                 (']' in netloc and '[' not in netloc)):
             raise ValueError("Invalid IPv6 URL")
+        if '[' in netloc and ']' in netloc:
+            bracketed_host = netloc.partition('[')[2].partition(']')[0]
+            _check_bracketed_host(bracketed_host)
     if allow_fragments and '#' in url:
         url, fragment = url.split('#', 1)
     if '?' in url:

Misc/NEWS.d/next/Library/2023-04-26-09-54-25.gh-issue-103848.aDSnpR.rst

@@ -0,0 +1,2 @@
+Add checks to ensure that ``[`` bracketed ``]`` hosts found by
+:func:`urllib.parse.urlsplit` are of IPv6 or IPvFuture format.