bpo-39073: validate Address parts to disallow CRLF (GH-19007) (#19224)

Disallow CR or LF in email.headerregistry.Address arguments to guard against header injection attacks.
(cherry picked from commit 614f17211c5fc0e5b828be1d3320661d1038fe8f)

Co-authored-by: Ashwin Ramaswami <aramaswamis@gmail.com>
Co-authored-by: Ashwin Ramaswami <aramaswamis@gmail.com>

diff --git a/Lib/email/headerregistry.py b/Lib/email/headerregistry.py
index f5be87f4d24368e5a4a419dde0b857968c44850c..6e86b3b26c92fab6ace64d195010ce8ebec4cbcd 100644 (file)
--- a/Lib/email/headerregistry.py
+++ b/Lib/email/headerregistry.py
@@ -31,6 +31,11 @@ class Address:
         without any Content Transfer Encoding.
 
         """
+
+        inputs = ''.join(filter(None, (display_name, username, domain, addr_spec)))
+        if '\r' in inputs or '\n' in inputs:
+            raise ValueError("invalid arguments; address parts cannot contain CR or LF")
+
         # This clause with its potential 'raise' may only happen when an
         # application program creates an Address object using an addr_spec
         # keyword.  The email library code itself must always supply username

diff --git a/Lib/test/test_email/test_headerregistry.py b/Lib/test/test_email/test_headerregistry.py
index d1007099f666c914b574c1aa42395112c7c1b0a4..08634daa7f61737f694337aa6074358c56190c1f 100644 (file)
--- a/Lib/test/test_email/test_headerregistry.py
+++ b/Lib/test/test_email/test_headerregistry.py
@@ -1435,6 +1435,25 @@ class TestAddressAndGroup(TestEmailBase):
     #    with self.assertRaises(ValueError):
     #        Address('foo', 'wők', 'example.com')
 
+    def test_crlf_in_constructor_args_raises(self):
+        cases = (
+            dict(display_name='foo\r'),
+            dict(display_name='foo\n'),
+            dict(display_name='foo\r\n'),
+            dict(domain='example.com\r'),
+            dict(domain='example.com\n'),
+            dict(domain='example.com\r\n'),
+            dict(username='wok\r'),
+            dict(username='wok\n'),
+            dict(username='wok\r\n'),
+            dict(addr_spec='wok@example.com\r'),
+            dict(addr_spec='wok@example.com\n'),
+            dict(addr_spec='wok@example.com\r\n')
+        )
+        for kwargs in cases:
+            with self.subTest(kwargs=kwargs), self.assertRaisesRegex(ValueError, "invalid arguments"):
+                Address(**kwargs)
+
     def test_non_ascii_username_in_addr_spec_raises(self):
         with self.assertRaises(ValueError):
             Address('foo', addr_spec='wők@example.com')

diff --git a/Misc/NEWS.d/next/Security/2020-03-15-01-28-36.bpo-39073.6Szd3i.rst b/Misc/NEWS.d/next/Security/2020-03-15-01-28-36.bpo-39073.6Szd3i.rst
new file mode 100644 (file)
index 0000000..6c9447b
--- /dev/null
+++ b/Misc/NEWS.d/next/Security/2020-03-15-01-28-36.bpo-39073.6Szd3i.rst
@@ -0,0 +1 @@
+Disallow CR or LF in email.headerregistry.Address arguments to guard against header injection attacks.