From 90d56127ae15b1e452755e62c77dc475dedf7161 Mon Sep 17 00:00:00 2001 From: jpic Date: Wed, 17 Jul 2019 23:54:25 +0200 Subject: [PATCH] bpo-34155: Dont parse domains containing @ (GH-13079) Before: >>> email.message_from_string('From: a@malicious.org@important.com', policy=email.policy.default)['from'].addresses (Address(display_name='', username='a', domain='malicious.org'),) >>> parseaddr('a@malicious.org@important.com') ('', 'a@malicious.org') After: >>> email.message_from_string('From: a@malicious.org@important.com', policy=email.policy.default)['from'].addresses (Address(display_name='', username='', domain=''),) >>> parseaddr('a@malicious.org@important.com') ('', 'a@') https://bugs.python.org/issue34155 Upstream-Status: Backport [https://github.com/python/cpython/commit/8cb65d1381b027f0b09ee36bfed7f35bb4dec9a9] CVE: CVE-2019-16056 Signed-off-by: Chen Qi --- Lib/email/_header_value_parser.py | 2 ++ Lib/email/_parseaddr.py | 11 ++++++++++- Lib/test/test_email/test__header_value_parser.py | 10 ++++++++++ Lib/test/test_email/test_email.py | 14 ++++++++++++++ .../2019-05-04-13-33-37.bpo-34155.MJll68.rst | 1 + 5 files changed, 37 insertions(+), 1 deletion(-) create mode 100644 Misc/NEWS.d/next/Security/2019-05-04-13-33-37.bpo-34155.MJll68.rst diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py index fc00b4a098..bbc026ec71 100644 --- a/Lib/email/_header_value_parser.py +++ b/Lib/email/_header_value_parser.py @@ -1582,6 +1582,8 @@ def get_domain(value): token, value = get_dot_atom(value) except errors.HeaderParseError: token, value = get_atom(value) + if value and value[0] == '@': + raise errors.HeaderParseError('Invalid Domain') if leader is not None: token[:0] = [leader] domain.append(token) diff --git a/Lib/email/_parseaddr.py b/Lib/email/_parseaddr.py index cdfa3729ad..41ff6f8c00 100644 --- a/Lib/email/_parseaddr.py +++ b/Lib/email/_parseaddr.py @@ -379,7 +379,12 @@ class AddrlistClass: aslist.append('@') self.pos += 1 self.gotonext() - return EMPTYSTRING.join(aslist) + self.getdomain() + domain = self.getdomain() + if not domain: + # Invalid domain, return an empty address instead of returning a + # local part to denote failed parsing. + return EMPTYSTRING + return EMPTYSTRING.join(aslist) + domain def getdomain(self): """Get the complete domain name from an address.""" @@ -394,6 +399,10 @@ class AddrlistClass: elif self.field[self.pos] == '.': self.pos += 1 sdlist.append('.') + elif self.field[self.pos] == '@': + # bpo-34155: Don't parse domains with two `@` like + # `a@malicious.org@important.com`. + return EMPTYSTRING elif self.field[self.pos] in self.atomends: break else: diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py index 693487bc96..7dc4de1b7b 100644 --- a/Lib/test/test_email/test__header_value_parser.py +++ b/Lib/test/test_email/test__header_value_parser.py @@ -1438,6 +1438,16 @@ class TestParser(TestParserMixin, TestEmailBase): self.assertEqual(addr_spec.domain, 'example.com') self.assertEqual(addr_spec.addr_spec, 'star.a.star@example.com') + def test_get_addr_spec_multiple_domains(self): + with self.assertRaises(errors.HeaderParseError): + parser.get_addr_spec('star@a.star@example.com') + + with self.assertRaises(errors.HeaderParseError): + parser.get_addr_spec('star@a@example.com') + + with self.assertRaises(errors.HeaderParseError): + parser.get_addr_spec('star@172.17.0.1@example.com') + # get_obs_route def test_get_obs_route_simple(self): diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py index c29cc56203..aa775881c5 100644 --- a/Lib/test/test_email/test_email.py +++ b/Lib/test/test_email/test_email.py @@ -3041,6 +3041,20 @@ class TestMiscellaneous(TestEmailBase): self.assertEqual(utils.parseaddr('<>'), ('', '')) self.assertEqual(utils.formataddr(utils.parseaddr('<>')), '') + def test_parseaddr_multiple_domains(self): + self.assertEqual( + utils.parseaddr('a@b@c'), + ('', '') + ) + self.assertEqual( + utils.parseaddr('a@b.c@c'), + ('', '') + ) + self.assertEqual( + utils.parseaddr('a@172.17.0.1@c'), + ('', '') + ) + def test_noquote_dump(self): self.assertEqual( utils.formataddr(('A Silly Person', 'person@dom.ain')), diff --git a/Misc/NEWS.d/next/Security/2019-05-04-13-33-37.bpo-34155.MJll68.rst b/Misc/NEWS.d/next/Security/2019-05-04-13-33-37.bpo-34155.MJll68.rst new file mode 100644 index 0000000000..50292e29ed --- /dev/null +++ b/Misc/NEWS.d/next/Security/2019-05-04-13-33-37.bpo-34155.MJll68.rst @@ -0,0 +1 @@ +Fix parsing of invalid email addresses with more than one ``@`` (e.g. a@b@c.com.) to not return the part before 2nd ``@`` as valid email address. Patch by maxking & jpic.