pool/python310
SHA256
2
0
Fork 1
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
b05afb7bf2
python310/CVE-2024-6923-email-hdr-inject.patch
Matej Cepl ca334cc307 - Adding bso1227999-reproducible-builds.patch fixing bsc#1227999 
adding reproducibility patches from gh#python/cpython!121872
  and gh#python/cpython!121883.

OBS-URL: https://build.opensuse.org/package/show/devel:languages:python:Factory/python310?expand=0&rev=140
2024-08-07 20:30:36 +00:00

336 lines
13 KiB
Diff
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

From ff3629b3cedf5e50a7a5f567283778fe5539a11e Mon Sep 17 00:00:00 2001
From: Petr Viktorin <encukou@gmail.com>
Date: Wed, 31 Jul 2024 00:19:48 +0200
Subject: [PATCH] [3.10] gh-121650: Encode newlines in headers, and verify
headers are sound (GH-122233)
Per RFC 2047:
> [...] these encoding schemes allow the
> encoding of arbitrary octet values, mail readers that implement this
> decoding should also ensure that display of the decoded data on the
> recipient's terminal will not cause unwanted side-effects
It seems that the "quoted-word" scheme is a valid way to include
a newline character in a header value, just like we already allow
undecodable bytes or control characters.
They do need to be properly quoted when serialized to text, though.
This should fail for custom fold() implementations that aren't careful
about newlines.
(cherry picked from commit 097633981879b3c9de9a1dd120d3aa585ecc2384)
Co-authored-by: Petr Viktorin <encukou@gmail.com>
Co-authored-by: Bas Bloemsaat <bas@bloemsaat.org>
Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
---
Doc/library/email.errors.rst | 6
Doc/library/email.policy.rst | 18 ++
Doc/whatsnew/3.10.rst | 12 +
Lib/email/_header_value_parser.py | 12 +
Lib/email/_policybase.py | 8 +
Lib/email/errors.py | 4
Lib/email/generator.py | 13 +-
Lib/test/test_email/test_generator.py | 62 ++++++++++
Lib/test/test_email/test_policy.py | 26 ++++
Misc/NEWS.d/next/Library/2024-07-27-16-10-41.gh-issue-121650.nf6oc9.rst | 5
10 files changed, 162 insertions(+), 4 deletions(-)
create mode 100644 Misc/NEWS.d/next/Library/2024-07-27-16-10-41.gh-issue-121650.nf6oc9.rst
--- a/Doc/library/email.errors.rst
+++ b/Doc/library/email.errors.rst
@@ -59,6 +59,12 @@ The following exception classes are defi
:class:`~email.mime.image.MIMEImage`).
+.. exception:: HeaderWriteError()
+
+ Raised when an error occurs when the :mod:`~email.generator` outputs
+ headers.
+
+
Here is the list of the defects that the :class:`~email.parser.FeedParser`
can find while parsing messages. Note that the defects are added to the message
where the problem was found, so for example, if a message nested inside a
--- a/Doc/library/email.policy.rst
+++ b/Doc/library/email.policy.rst
@@ -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:: 3.10.15
+
+
The following :class:`Policy` method is intended to be called by code using
the email library to create policy instances with custom settings:
--- a/Doc/whatsnew/3.10.rst
+++ b/Doc/whatsnew/3.10.rst
@@ -2357,3 +2357,15 @@ ipaddress
* Fixed ``is_global`` and ``is_private`` behavior in ``IPv4Address``,
``IPv6Address``, ``IPv4Network`` and ``IPv6Network``.
+
+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`.)
--- a/Lib/email/_header_value_parser.py
+++ b/Lib/email/_header_value_parser.py
@@ -92,6 +92,8 @@ TOKEN_ENDS = TSPECIALS | WSP
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'\"')+'"'
@@ -2778,9 +2780,13 @@ def _refold_parse_tree(parse_tree, *, po
wrap_as_ew_blocked -= 1
continue
tstr = str(part)
- if part.token_type == 'ptext' and set(tstr) & SPECIALS:
- # Encode if tstr contains special characters.
- want_encoding = True
+ if not want_encoding:
+ if part.token_type == 'ptext':
+ # Encode if tstr contains special characters.
+ want_encoding = not SPECIALSNL.isdisjoint(tstr)
+ else:
+ # Encode if tstr contains newlines.
+ want_encoding = not NLSET.isdisjoint(tstr)
try:
tstr.encode(encoding)
charset = encoding
--- a/Lib/email/_policybase.py
+++ b/Lib/email/_policybase.py
@@ -157,6 +157,13 @@ class Policy(_PolicyBase, metaclass=abc.
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.
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.
--- a/Lib/email/errors.py
+++ b/Lib/email/errors.py
@@ -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."""
--- a/Lib/email/generator.py
+++ b/Lib/email/generator.py
@@ -14,12 +14,14 @@ import random
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]')
@@ -223,7 +225,16 @@ class Generator:
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)
--- a/Lib/test/test_email/test_generator.py
+++ b/Lib/test/test_email/test_generator.py
@@ -6,6 +6,7 @@ from email.message import EmailMessage
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
@@ -216,6 +217,44 @@ class TestGeneratorBase:
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):
@@ -224,6 +263,29 @@ class TestGenerator(TestGeneratorBase, T
ioclass = io.StringIO
typ = str
+ 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):
--- a/Lib/test/test_email/test_policy.py
+++ b/Lib/test/test_email/test_policy.py
@@ -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.
@@ -277,6 +278,31 @@ class PolicyAPITests(unittest.TestCase):
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)
+
+ 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).
--- /dev/null
+++ 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`.)
Reference in New Issue View Git Blame Copy Permalink