python · encukou · Jul 30, 2024 · Jul 24, 2024 · Jul 24, 2024 · Jul 27, 2024
@@ -51,13 +51,20 @@
   :mimetype:`multipart` or missing.  :exc:`MultipartConversionError` multiply
   inherits from :exc:`MessageError` and the built-in :exc:`TypeError`.

   Since :meth:`Message.add_payload` is deprecated, this exception is rarely
   raised in practice.  However the exception may also be raised if the
   :meth:`~email.message.Message.attach`
   method is called on an instance of a class derived from
   :class:`~email.mime.nonmultipart.MIMENonMultipart` (e.g.
   :class:`~email.mime.image.MIMEImage`).

+
+.. exception:: HeaderWriteError()
+
+   Raised when an error occurs when the :mod:`~email.generator` outputs
+   headers.
+
+
 .. exception:: MessageDefect()

   This is the base class for all defects found when parsing email messages.

@@ -229,6 +229,24 @@ added matters.  To illustrate::

      .. versionadded:: 3.6

+
+   .. attribute:: verify_generated_headers
+
+      If ``True`` (the default), the generator will raise
+      :exc:`~email.errors.HeaderWriteError` instead of writing a header
+      that is improperly folded or delimited, such that it would
+      be parsed as multiple headers or joined with adjacent data.
+      Such headers can be generated by custom header classes or bugs
+      in the ``email`` module.
+
+      As it's a security feature, this defaults to ``True`` even in the
+      :class:`~email.policy.Compat32` policy.
+      For backwards compatible, but unsafe, behavior, it must be set to
+      ``False`` explicitly.
+
+      .. versionadded:: 3.13
+
+
   The following :class:`Policy` method is intended to be called by code using
   the email library to create policy instances with custom settings:


diff --git a/Doc/whatsnew/3.13.rst b/Doc/whatsnew/3.13.rst
@@ -736,6 +736,15 @@ doctest
 email
 -----

+* Headers with embedded newlines are now quoted on output.
+
+  The :mod:`~email.generator` will now refuse to serialize (write) headers
+  that are improperly folded or delimited, such that they would be parsed as
+  multiple headers or joined with adjacent data.
+  If you need to turn this safety feature off,
+  set :attr:`~email.policy.Policy.verify_generated_headers`.
+  (Contributed by Bas Bloemsaat and Petr Viktorin in :gh:`121650`.)
+
 * :func:`email.utils.getaddresses` and :func:`email.utils.parseaddr` now return
  ``('', '')`` 2-tuples in more situations where invalid email addresses are
  encountered instead of potentially inaccurate values. Add optional *strict*

@@ -92,6 +92,8 @@
 ASPECIALS = TSPECIALS | set("*'%")
 ATTRIBUTE_ENDS = ASPECIALS | WSP
 EXTENDED_ATTRIBUTE_ENDS = ATTRIBUTE_ENDS - set('%')
+NLSET = {'\n', '\r'}
+SPECIALSNL = SPECIALS | NLSET

 def quote_string(value):
    return '"'+str(value).replace('\\', '\\\\').replace('"', r'\"')+'"'
@@ -2802,9 +2804,12 @@ def _refold_parse_tree(parse_tree, *, policy):
            wrap_as_ew_blocked -= 1
            continue
        tstr = str(part)
-        if part.token_type == 'ptext' and set(tstr) & SPECIALS:
+        if part.token_type == 'ptext' and set(tstr) & SPECIALSNL:
            # Encode if tstr contains special characters.
            want_encoding = True
+        elif set(tstr) & NLSET:
+            # Encode if text contains newlines
+            want_encoding = True
        try:
            tstr.encode(encoding)
            charset = encoding

@@ -157,6 +157,13 @@ class Policy(_PolicyBase, metaclass=abc.ABCMeta):
    message_factory     -- the class to use to create new message objects.
                           If the value is None, the default is Message.

+    verify_generated_headers
+                        -- if true, the generator verifies that each header
+                           they are properly folded, so that a parser won't
+                           treat it as multiple headers, start-of-body, or
+                           part of another header.
+                           This is a check against custom Header & fold()
+                           implementations.
    """

    raise_on_defect = False
@@ -165,6 +172,7 @@ class Policy(_PolicyBase, metaclass=abc.ABCMeta):
    max_line_length = 78
    mangle_from_ = False
    message_factory = None
+    verify_generated_headers = True

    def handle_defect(self, obj, defect):
        """Based on policy, either raise defect or call register_defect.

@@ -29,6 +29,10 @@ class CharsetError(MessageError):
    """An illegal charset was given."""


+class HeaderWriteError(MessageError):
+    """Error while writing headers."""
+
+
 # These are parsing defects which the parser was able to work around.
 class MessageDefect(ValueError):
    """Base class for a message defect."""

@@ -14,12 +14,14 @@
 from copy import deepcopy
 from io import StringIO, BytesIO
 from email.utils import _has_surrogates
+from email.errors import HeaderWriteError

 UNDERSCORE = '_'
 NL = '\n'  # XXX: no longer used by the code below.

 NLCRE = re.compile(r'\r\n|\r|\n')
 fcre = re.compile(r'^From ', re.MULTILINE)
+NEWLINE_WITHOUT_FWSP = re.compile(r'\r\n[^ \t]|\r[^ \n\t]|\n[^ \t]')


 class Generator:
@@ -222,7 +224,16 @@ def _dispatch(self, msg):

    def _write_headers(self, msg):
        for h, v in msg.raw_items():
-            self.write(self.policy.fold(h, v))
+            folded = self.policy.fold(h, v)
+            if self.policy.verify_generated_headers:
+                linesep = self.policy.linesep
+                if not folded.endswith(self.policy.linesep):
+                    raise HeaderWriteError(
+                        f'folded header does not end with {linesep!r}: {folded!r}')
+                if NEWLINE_WITHOUT_FWSP.search(folded.removesuffix(linesep)):
+                    raise HeaderWriteError(
+                        f'folded header contains newline: {folded!r}')
+            self.write(folded)
        # A blank line always separates headers from body
        self.write(self._NL)


@@ -6,6 +6,7 @@
 from email.generator import Generator, BytesGenerator
 from email.headerregistry import Address
 from email import policy
+import email.errors
 from test.test_email import TestEmailBase, parameterize


@@ -249,6 +250,44 @@ def test_rfc2231_wrapping_switches_to_default_len_if_too_narrow(self):
        g.flatten(msg)
        self.assertEqual(s.getvalue(), self.typ(expected))

+    def test_keep_encoded_newlines(self):
+        msg = self.msgmaker(self.typ(textwrap.dedent("""\
+            To: nobody
+            Subject: Bad subject=?UTF-8?Q?=0A?=Bcc: injection@example.com
+
+            None
+            """)))
+        expected = textwrap.dedent("""\
+            To: nobody
+            Subject: Bad subject=?UTF-8?Q?=0A?=Bcc: injection@example.com
+
+            None
+            """)
+        s = self.ioclass()
+        g = self.genclass(s, policy=self.policy.clone(max_line_length=80))
+        g.flatten(msg)
+        self.assertEqual(s.getvalue(), self.typ(expected))
+
+    def test_keep_long_encoded_newlines(self):
+        msg = self.msgmaker(self.typ(textwrap.dedent("""\
+            To: nobody
+            Subject: Bad subject=?UTF-8?Q?=0A?=Bcc: injection@example.com
+
+            None
+            """)))
+        expected = textwrap.dedent("""\
+            To: nobody
+            Subject: Bad subject
+             =?utf-8?q?=0A?=Bcc:
+             injection@example.com
+
+            None
+            """)
+        s = self.ioclass()
+        g = self.genclass(s, policy=self.policy.clone(max_line_length=30))
+        g.flatten(msg)
+        self.assertEqual(s.getvalue(), self.typ(expected))
+

 class TestGenerator(TestGeneratorBase, TestEmailBase):

@@ -273,6 +312,29 @@ def test_flatten_unicode_linesep(self):
        g.flatten(msg)
        self.assertEqual(s.getvalue(), self.typ(expected))

+    def test_verify_generated_headers(self):
+        """gh-121650: by default the generator prevents header injection"""
+        class LiteralHeader(str):
+            name = 'Header'
+            def fold(self, **kwargs):
+                return self
+
+        for text in (
+            'Value\r\nBad Injection\r\n',
+            'NoNewLine'
+        ):
+            with self.subTest(text=text):
+                message = message_from_string(
+                    "Header: Value\r\n\r\nBody",
+                    policy=self.policy,
+                )
+
+                del message['Header']
+                message['Header'] = LiteralHeader(text)
+
+                with self.assertRaises(email.errors.HeaderWriteError):
+                    message.as_string()
+

 class TestBytesGenerator(TestGeneratorBase, TestEmailBase):


@@ -26,6 +26,7 @@ class PolicyAPITests(unittest.TestCase):
        'raise_on_defect':          False,
        'mangle_from_':             True,
        'message_factory':          None,
+        'verify_generated_headers': True,
        }
    # These default values are the ones set on email.policy.default.
    # If any of these defaults change, the docs must be updated.
@@ -294,6 +295,32 @@ def test_short_maxlen_error(self):
                with self.assertRaises(email.errors.HeaderParseError):
                    policy.fold("Subject", subject)

+    def test_verify_generated_headers(self):
+        """Turning protection off allows header injection"""
+        policy = email.policy.default.clone(verify_generated_headers=False)
+        for text in (
+            'Header: Value\r\nBad: Injection\r\n',
+            'Header: NoNewLine'
+        ):
+            with self.subTest(text=text):
+                message = email.message_from_string(
+                    "Header: Value\r\n\r\nBody",
+                    policy=policy,
+                )
+                class LiteralHeader(str):
+                    name = 'Header'
+                    def fold(self, **kwargs):
+                        return self
+
+                del message['Header']
+                message['Header'] = LiteralHeader(text)
+
+                expected = text#.replace('\r\n', '\n')
+                self.assertEqual(
+                    message.as_string(),
+                    f"{text}\nBody",
+                )
+
    # XXX: Need subclassing tests.
    # For adding subclassed objects, make sure the usual rules apply (subclass
    # wins), but that the order still works (right overrides left).

diff --git a/Misc/NEWS.d/next/Library/2024-07-27-16-10-41.gh-issue-121650.nf6oc9.rst b/Misc/NEWS.d/next/Library/2024-07-27-16-10-41.gh-issue-121650.nf6oc9.rst
@@ -0,0 +1,5 @@
+:mod:`email` headers with embedded newlines are now quoted on output. The
+:mod:`~email.generator` will now refuse to serialize (write) headers that
+are unsafely folded or delimited; see
+:attr:`~email.policy.Policy.verify_generated_headers`. (Contributed by Bas
+Bloemsaat and Petr Viktorin in :gh:`121650`.)