Sanitise Content-Type of media proxy URLs

Just as with uploads and emoji before, this can otherwise be used
to place counterfeit AP objects or other malicious payloads.
In this case, even if we never assign a priviliged type to content,
the remote server can and until now we just mimcked whatever it told us.

Preview URLs already handle only specific, safe content types
and redirect to the external host for all else; thus no additional
sanitisiation is needed for them.

Non-previews are all delegated to the modified ReverseProxy module.
It already has consolidated logic for building response headers
making it easy to slip in sanitisation.

Although proxy urls are prefixed by a MAC built from a server secret,
attackers can still achieve a perfect id match when they are able to
change the contents of the pointed to URL. After sending an posts
containing an attachment at a controlled destination, the proxy URL can
be read back and inserted into the payload. After injection of
counterfeits in the target server the content can again be changed
to something innocuous lessening chance of detection.

lib/pleroma/reverse_proxy.ex

@@ -17,6 +17,8 @@ defmodule Pleroma.ReverseProxy do
   @failed_request_ttl :timer.seconds(60)
   @methods ~w(GET HEAD)
 
+  @allowed_mime_types Pleroma.Config.get([Pleroma.Upload, :allowed_mime_types], [])
+
   @cachex Pleroma.Config.get([:cachex, :provider], Cachex)
 
   def max_read_duration_default, do: @max_read_duration
@@ -253,6 +255,7 @@ defmodule Pleroma.ReverseProxy do
     headers
     |> Enum.filter(fn {k, _} -> k in @keep_resp_headers end)
     |> build_resp_cache_headers(opts)
+    |> sanitise_content_type()
     |> build_resp_content_disposition_header(opts)
     |> build_csp_headers()
     |> Keyword.merge(Keyword.get(opts, :resp_headers, []))
@@ -282,6 +285,21 @@ defmodule Pleroma.ReverseProxy do
     end
   end
 
+  defp sanitise_content_type(headers) do
+    original_ct = get_content_type(headers)
+
+    safe_ct =
+      Pleroma.Web.Plugs.Utils.get_safe_mime_type(
+        %{allowed_mime_types: @allowed_mime_types},
+        original_ct
+      )
+
+    [
+      {"content-type", safe_ct}
+      | Enum.filter(headers, fn {k, _v} -> k != "content-type" end)
+    ]
+  end
+
   defp build_resp_content_disposition_header(headers, opts) do
     opt = Keyword.get(opts, :inline_content_types, @inline_content_types)
 

test/pleroma/reverse_proxy_test.exs

@@ -75,13 +75,16 @@ defmodule Pleroma.ReverseProxyTest do
       Tesla.Mock.mock(fn %{method: :head, url: "/head"} ->
         %Tesla.Env{
           status: 200,
-          headers: [{"content-type", "text/html; charset=utf-8"}],
+          headers: [{"content-type", "image/png"}],
           body: ""
         }
       end)
 
       conn = ReverseProxy.call(Map.put(conn, :method, "HEAD"), "/head")
-      assert html_response(conn, 200) == ""
+
+      assert conn.status == 200
+      assert Conn.get_resp_header(conn, "content-type") == ["image/png"]
+      assert conn.resp_body == ""
     end
   end
 
@@ -252,4 +255,38 @@ defmodule Pleroma.ReverseProxyTest do
       assert {"content-disposition", "attachment; filename=\"filename.jpg\""} in conn.resp_headers
     end
   end
+
+  describe "content-type sanitisation" do
+    test "preserves video type", %{conn: conn} do
+      Tesla.Mock.mock(fn %{method: :get, url: "/content"} ->
+        %Tesla.Env{
+          status: 200,
+          headers: [{"content-type", "video/mp4"}],
+          body: "test"
+        }
+      end)
+
+      conn = ReverseProxy.call(Map.put(conn, :method, "GET"), "/content")
+
+      assert conn.status == 200
+      assert Conn.get_resp_header(conn, "content-type") == ["video/mp4"]
+      assert conn.resp_body == "test"
+    end
+
+    test "replaces application type", %{conn: conn} do
+      Tesla.Mock.mock(fn %{method: :get, url: "/content"} ->
+        %Tesla.Env{
+          status: 200,
+          headers: [{"content-type", "application/activity+json"}],
+          body: "test"
+        }
+      end)
+
+      conn = ReverseProxy.call(Map.put(conn, :method, "GET"), "/content")
+
+      assert conn.status == 200
+      assert Conn.get_resp_header(conn, "content-type") == ["application/octet-stream"]
+      assert conn.resp_body == "test"
+    end
+  end
 end