[3.7] gh-104049: do not expose on-disk location from SimpleHTTPRequestHandler (GH-104122)

Do not expose the local server's on-disk location from `SimpleHTTPRequestHandler` when generating a directory index. (unnecessary information disclosure)

(cherry picked from commit c7c3a60)

Co-authored-by: Ethan Furman <[email protected]>
Co-authored-by: Gregory P. Smith <[email protected]>
Co-authored-by: Jelle Zijlstra <[email protected]>

Author: 4 people

Lib/http/server.py

@@ -777,7 +777,7 @@ def list_directory(self, path):
             displaypath = urllib.parse.unquote(self.path,
                                                errors='surrogatepass')
         except UnicodeDecodeError:
-            displaypath = urllib.parse.unquote(path)
+            displaypath = urllib.parse.unquote(self.path)
         displaypath = html.escape(displaypath, quote=False)
         enc = sys.getfilesystemencoding()
         title = 'Directory listing for %s' % displaypath

Lib/test/test_httpservers.py

@@ -413,6 +413,14 @@ def test_undecodable_filename(self):
         self.check_status_and_reason(response, HTTPStatus.OK,
                                      data=support.TESTFN_UNDECODABLE)
 
+    def test_undecodable_parameter(self):
+        # sanity check using a valid parameter
+        response = self.request(self.base_url + '/?x=123').read()
+        self.assertRegex(response, f'listing for {self.base_url}/\?x=123'.encode('latin1'))
+        # now the bogus encoding
+        response = self.request(self.base_url + '/?x=%bb').read()
+        self.assertRegex(response, f'listing for {self.base_url}/\?x=\xef\xbf\xbd'.encode('latin1'))
+
     def test_get_dir_redirect_location_domain_injection_bug(self):
         """Ensure //evil.co/..%2f../../X does not put //evil.co/ in Location.
 

Misc/NEWS.d/next/Security/2023-05-01-15-03-25.gh-issue-104049.b01Y3g.rst

@@ -0,0 +1,2 @@
+Do not expose the local on-disk location in directory indexes
+produced by :class:`http.client.SimpleHTTPRequestHandler`.