Fix unsafe hotserving behaviour for non-multimedia uploads. (#15680)

* Fix unsafe hotserving behaviour for non-multimedia uploads.

* invert disposition assert

* test_media_storage.py: run lint

* test_base.py: /inline/attachment/s

* Only return attachment for disposition type, update tests

* Update synapse/media/_base.py

Co-authored-by: Patrick Cloke <clokep@users.noreply.github.com>

* Update changelog.d/15680.bugfix

Co-authored-by: Patrick Cloke <clokep@users.noreply.github.com>

* add attribution

* Update changelog.

---------

Co-authored-by: Patrick Cloke <clokep@users.noreply.github.com>

changelog.d/15680.bugfix

@@ -0,0 +1 @@
+Fix a long-standing bug where media files were served in an unsafe manner. Contributed by @joshqou.

synapse/media/_base.py

@@ -152,6 +152,9 @@ def _quote(x: str) -> str:
         content_type = media_type
 
     request.setHeader(b"Content-Type", content_type.encode("UTF-8"))
+
+    # Use a Content-Disposition of attachment to force download of media.
+    disposition = "attachment"
     if upload_name:
         # RFC6266 section 4.1 [1] defines both `filename` and `filename*`.
         #
@@ -173,11 +176,17 @@ def _quote(x: str) -> str:
         # correctly interpret those as of 0.99.2 and (b) they are a bit of a pain and we
         # may as well just do the filename* version.
         if _can_encode_filename_as_token(upload_name):
-            disposition = "inline; filename=%s" % (upload_name,)
+            disposition = "%s; filename=%s" % (
+                disposition,
+                upload_name,
+            )
         else:
-            disposition = "inline; filename*=utf-8''%s" % (_quote(upload_name),)
+            disposition = "%s; filename*=utf-8''%s" % (
+                disposition,
+                _quote(upload_name),
+            )
 
-        request.setHeader(b"Content-Disposition", disposition.encode("ascii"))
+    request.setHeader(b"Content-Disposition", disposition.encode("ascii"))
 
     # cache for at least a day.
     # XXX: we might want to turn this off for data we don't want to

tests/media/test_base.py

@@ -20,12 +20,12 @@
 class GetFileNameFromHeadersTests(unittest.TestCase):
     # input -> expected result
     TEST_CASES = {
-        b"inline; filename=abc.txt": "abc.txt",
-        b'inline; filename="azerty"': "azerty",
-        b'inline; filename="aze%20rty"': "aze%20rty",
-        b'inline; filename="aze"rty"': 'aze"rty',
-        b'inline; filename="azer;ty"': "azer;ty",
-        b"inline; filename*=utf-8''foo%C2%A3bar": "foo£bar",
+        b"attachment; filename=abc.txt": "abc.txt",
+        b'attachment; filename="azerty"': "azerty",
+        b'attachment; filename="aze%20rty"': "aze%20rty",
+        b'attachment; filename="aze"rty"': 'aze"rty',
+        b'attachment; filename="azer;ty"': "azer;ty",
+        b"attachment; filename*=utf-8''foo%C2%A3bar": "foo£bar",
     }
 
     def tests(self) -> None:

tests/media/test_media_storage.py

@@ -317,7 +317,7 @@ def _req(
 
     def test_handle_missing_content_type(self) -> None:
         channel = self._req(
-            b"inline; filename=out" + self.test_image.extension,
+            b"attachment; filename=out" + self.test_image.extension,
             include_content_type=False,
         )
         headers = channel.headers
@@ -331,15 +331,15 @@ def test_disposition_filename_ascii(self) -> None:
         If the filename is filename=<ascii> then Synapse will decode it as an
         ASCII string, and use filename= in the response.
         """
-        channel = self._req(b"inline; filename=out" + self.test_image.extension)
+        channel = self._req(b"attachment; filename=out" + self.test_image.extension)
 
         headers = channel.headers
         self.assertEqual(
             headers.getRawHeaders(b"Content-Type"), [self.test_image.content_type]
         )
         self.assertEqual(
             headers.getRawHeaders(b"Content-Disposition"),
-            [b"inline; filename=out" + self.test_image.extension],
+            [b"attachment; filename=out" + self.test_image.extension],
         )
 
     def test_disposition_filenamestar_utf8escaped(self) -> None:
@@ -350,7 +350,7 @@ def test_disposition_filenamestar_utf8escaped(self) -> None:
         """
         filename = parse.quote("\u2603".encode()).encode("ascii")
         channel = self._req(
-            b"inline; filename*=utf-8''" + filename + self.test_image.extension
+            b"attachment; filename*=utf-8''" + filename + self.test_image.extension
         )
 
         headers = channel.headers
@@ -359,21 +359,21 @@ def test_disposition_filenamestar_utf8escaped(self) -> None:
         )
         self.assertEqual(
             headers.getRawHeaders(b"Content-Disposition"),
-            [b"inline; filename*=utf-8''" + filename + self.test_image.extension],
+            [b"attachment; filename*=utf-8''" + filename + self.test_image.extension],
         )
 
     def test_disposition_none(self) -> None:
         """
-        If there is no filename, one isn't passed on in the Content-Disposition
-        of the request.
+        If there is no filename, Content-Disposition should only
+        be a disposition type.
         """
         channel = self._req(None)
 
         headers = channel.headers
         self.assertEqual(
             headers.getRawHeaders(b"Content-Type"), [self.test_image.content_type]
         )
-        self.assertEqual(headers.getRawHeaders(b"Content-Disposition"), None)
+        self.assertEqual(headers.getRawHeaders(b"Content-Disposition"), [b"attachment"])
 
     def test_thumbnail_crop(self) -> None:
         """Test that a cropped remote thumbnail is available."""
@@ -612,7 +612,7 @@ def test_x_robots_tag_header(self) -> None:
         Tests that the `X-Robots-Tag` header is present, which informs web crawlers
         to not index, archive, or follow links in media.
         """
-        channel = self._req(b"inline; filename=out" + self.test_image.extension)
+        channel = self._req(b"attachment; filename=out" + self.test_image.extension)
 
         headers = channel.headers
         self.assertEqual(
@@ -625,7 +625,7 @@ def test_cross_origin_resource_policy_header(self) -> None:
         Test that the Cross-Origin-Resource-Policy header is set to "cross-origin"
         allowing web clients to embed media from the downloads API.
         """
-        channel = self._req(b"inline; filename=out" + self.test_image.extension)
+        channel = self._req(b"attachment; filename=out" + self.test_image.extension)
 
         headers = channel.headers