From 4cbcd2f8c4e12b912e4d21fd892eedf7a3813d8e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Roberto=20C=2E=20S=C3=A1nchez?= Date: Sat, 14 Sep 2019 13:26:38 -0400 Subject: [PATCH] [2.7] bpo-34155: Dont parse domains containing @ (GH-13079) (GH-16006) This change skips parsing of email addresses where domains include a "@" character, which can be maliciously used since the local part is returned as a complete address. (cherry picked from commit 8cb65d1381b027f0b09ee36bfed7f35bb4dec9a9) Excludes changes to Lib/email/_header_value_parser.py, which did not exist in 2.7. Co-authored-by: jpic https://bugs.python.org/issue34155 --- Lib/email/_parseaddr.py | 11 ++++++++++- Lib/email/test/test_email.py | 14 ++++++++++++++ .../2019-05-04-13-33-37.bpo-34155.MJll68.rst | 1 + 3 files changed, 25 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/_parseaddr.py b/Lib/email/_parseaddr.py index 690db2c22d34d..dc49d2e45a5eb 100644 --- a/Lib/email/_parseaddr.py +++ b/Lib/email/_parseaddr.py @@ -336,7 +336,12 @@ def getaddrspec(self): 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.""" @@ -351,6 +356,10 @@ def getdomain(self): 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/email/test/test_email.py b/Lib/email/test/test_email.py index 4b4dee3d34644..2efe44ac5a73f 100644 --- a/Lib/email/test/test_email.py +++ b/Lib/email/test/test_email.py @@ -2306,6 +2306,20 @@ def test_parseaddr_empty(self): 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 0000000000000..50292e29ed1d2 --- /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.