gh-87389: Fix an open redirection vulnerability in http.server. (GH-93879)

Fix an open redirection vulnerability in the `http.server` module when
an URI path starts with `//` that could produce a 301 Location header
with a misleading target.  Vulnerability discovered, and logic fix
proposed, by Hamza Avvan (@hamzaavvan).

Test and comments authored by Gregory P. Smith [Google].
(cherry picked from commit 4abab6b603)

Co-authored-by: Gregory P. Smith <greg@krypto.org>

Lib/http/server.py

@@ -329,6 +329,13 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler):
                 return False
         self.command, self.path = command, path
 
+        # gh-87389: The purpose of replacing '//' with '/' is to protect
+        # against open redirect attacks possibly triggered if the path starts
+        # with '//' because http clients treat //path as an absolute URI
+        # without scheme (similar to http://path) rather than a path.
+        if self.path.startswith('//'):
+            self.path = '/' + self.path.lstrip('/')  # Reduce to a single /
+
         # Examine the headers and look for a Connection directive.
         try:
             self.headers = http.client.parse_headers(self.rfile,

Lib/test/test_httpservers.py

@@ -334,7 +334,7 @@ class SimpleHTTPServerTestCase(BaseTestCase):
         pass
 
     def setUp(self):
-        BaseTestCase.setUp(self)
+        super().setUp()
         self.cwd = os.getcwd()
         basetempdir = tempfile.gettempdir()
         os.chdir(basetempdir)
@@ -362,7 +362,7 @@ class SimpleHTTPServerTestCase(BaseTestCase):
             except:
                 pass
         finally:
-            BaseTestCase.tearDown(self)
+            super().tearDown()
 
     def check_status_and_reason(self, response, status, data=None):
         def close_conn():
@@ -418,6 +418,55 @@ class SimpleHTTPServerTestCase(BaseTestCase):
         self.check_status_and_reason(response, HTTPStatus.OK,
                                      data=os_helper.TESTFN_UNDECODABLE)
 
+    def test_get_dir_redirect_location_domain_injection_bug(self):
+        """Ensure //evil.co/..%2f../../X does not put //evil.co/ in Location.
+
+        //netloc/ in a Location header is a redirect to a new host.
+        https://github.com/python/cpython/issues/87389
+
+        This checks that a path resolving to a directory on our server cannot
+        resolve into a redirect to another server.
+        """
+        os.mkdir(os.path.join(self.tempdir, 'existing_directory'))
+        url = f'/python.org/..%2f..%2f..%2f..%2f..%2f../%0a%0d/../{self.tempdir_name}/existing_directory'
+        expected_location = f'{url}/'  # /python.org.../ single slash single prefix, trailing slash
+        # Canonicalizes to /tmp/tempdir_name/existing_directory which does
+        # exist and is a dir, triggering the 301 redirect logic.
+        response = self.request(url)
+        self.check_status_and_reason(response, HTTPStatus.MOVED_PERMANENTLY)
+        location = response.getheader('Location')
+        self.assertEqual(location, expected_location, msg='non-attack failed!')
+
+        # //python.org... multi-slash prefix, no trailing slash
+        attack_url = f'/{url}'
+        response = self.request(attack_url)
+        self.check_status_and_reason(response, HTTPStatus.MOVED_PERMANENTLY)
+        location = response.getheader('Location')
+        self.assertFalse(location.startswith('//'), msg=location)
+        self.assertEqual(location, expected_location,
+                msg='Expected Location header to start with a single / and '
+                'end with a / as this is a directory redirect.')
+
+        # ///python.org... triple-slash prefix, no trailing slash
+        attack3_url = f'//{url}'
+        response = self.request(attack3_url)
+        self.check_status_and_reason(response, HTTPStatus.MOVED_PERMANENTLY)
+        self.assertEqual(response.getheader('Location'), expected_location)
+
+        # If the second word in the http request (Request-URI for the http
+        # method) is a full URI, we don't worry about it, as that'll be parsed
+        # and reassembled as a full URI within BaseHTTPRequestHandler.send_head
+        # so no errant scheme-less //netloc//evil.co/ domain mixup can happen.
+        attack_scheme_netloc_2slash_url = f'https://pypi.org/{url}'
+        expected_scheme_netloc_location = f'{attack_scheme_netloc_2slash_url}/'
+        response = self.request(attack_scheme_netloc_2slash_url)
+        self.check_status_and_reason(response, HTTPStatus.MOVED_PERMANENTLY)
+        location = response.getheader('Location')
+        # We're just ensuring that the scheme and domain make it through, if
+        # there are or aren't multiple slashes at the start of the path that
+        # follows that isn't important in this Location: header.
+        self.assertTrue(location.startswith('https://pypi.org/'), msg=location)
+
     def test_get(self):
         #constructs the path relative to the root directory of the HTTPServer
         response = self.request(self.base_url + '/test')

Misc/NEWS.d/next/Security/2022-06-15-20-09-23.gh-issue-87389.QVaC3f.rst

@@ -0,0 +1,3 @@
+:mod:`http.server`: Fix an open redirection vulnerability in the HTTP server
+when an URI path starts with ``//``.  Vulnerability discovered, and initial
+fix proposed, by Hamza Avvan.