html: lock down allowed class attributes to only those related to microformats

2 files changed, 110 insertions, 4 deletions

diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex
index b4a4742ee..bb1817b0d 100644
--- a/lib/pleroma/html.ex
+++ b/lib/pleroma/html.ex
@@ -94,14 +94,31 @@ defmodule Pleroma.HTML.Scrubber.TwitterText do
 
   # links
   Meta.allow_tag_with_uri_attributes("a", ["href", "data-user", "data-tag"], @valid_schemes)
-  Meta.allow_tag_with_these_attributes("a", ["name", "title", "class"])
+
+  Meta.allow_tag_with_this_attribute_values("a", "class", [
+    "hashtag",
+    "u-url",
+    "mention",
+    "u-url mention",
+    "mention u-url"
+  ])
+
+  Meta.allow_tag_with_this_attribute_values("a", "rel", [
+    "tag",
+    "nofollow",
+    "noopener",
+    "noreferrer"
+  ])
+
+  Meta.allow_tag_with_these_attributes("a", ["name", "title"])
 
   # paragraphs and linebreaks
   Meta.allow_tag_with_these_attributes("br", [])
   Meta.allow_tag_with_these_attributes("p", [])
 
   # microformats
-  Meta.allow_tag_with_these_attributes("span", ["class"])
+  Meta.allow_tag_with_this_attribute_values("span", "class", ["h-card"])
+  Meta.allow_tag_with_these_attributes("span", [])
 
   # allow inline images for custom emoji
   @allow_inline_images Keyword.get(@markup, :allow_inline_images)
@@ -135,7 +152,23 @@ defmodule Pleroma.HTML.Scrubber.Default do
   Meta.strip_comments()
 
   Meta.allow_tag_with_uri_attributes("a", ["href", "data-user", "data-tag"], @valid_schemes)
-  Meta.allow_tag_with_these_attributes("a", ["name", "title", "class"])
+
+  Meta.allow_tag_with_this_attribute_values("a", "class", [
+    "hashtag",
+    "u-url",
+    "mention",
+    "u-url mention",
+    "mention u-url"
+  ])
+
+  Meta.allow_tag_with_this_attribute_values("a", "rel", [
+    "tag",
+    "nofollow",
+    "noopener",
+    "noreferrer"
+  ])
+
+  Meta.allow_tag_with_these_attributes("a", ["name", "title"])
 
   Meta.allow_tag_with_these_attributes("abbr", ["title"])
 
@@ -150,11 +183,13 @@ defmodule Pleroma.HTML.Scrubber.Default do
   Meta.allow_tag_with_these_attributes("ol", [])
   Meta.allow_tag_with_these_attributes("p", [])
   Meta.allow_tag_with_these_attributes("pre", [])
-  Meta.allow_tag_with_these_attributes("span", ["class"])
   Meta.allow_tag_with_these_attributes("strong", [])
   Meta.allow_tag_with_these_attributes("u", [])
   Meta.allow_tag_with_these_attributes("ul", [])
 
+  Meta.allow_tag_with_this_attribute_values("span", "class", ["h-card"])
+  Meta.allow_tag_with_these_attributes("span", [])
+
   @allow_inline_images Keyword.get(@markup, :allow_inline_images)
 
   if @allow_inline_images do
diff --git a/test/html_test.exs b/test/html_test.exs
index 29cab17f3..f98e7745f 100644
--- a/test/html_test.exs
+++ b/test/html_test.exs
@@ -18,6 +18,18 @@ defmodule Pleroma.HTMLTest do
     <img src="http://example.com/image.jpg" onerror="alert('hacked')">
   """
 
+  @html_span_class_sample """
+    <span class="animate-spin">hi</span>
+  """
+
+  @html_span_microformats_sample """
+    <span class="h-card"><a class="u-url mention">@<span>foo</span></a></span>
+  """
+
+  @html_span_invalid_microformats_sample """
+    <span class="h-card"><a class="u-url mention animate-spin">@<span>foo</span></a></span>
+  """
+
   describe "StripTags scrubber" do
     test "works as expected" do
       expected = """
@@ -58,6 +70,36 @@ defmodule Pleroma.HTMLTest do
 
       assert expected == HTML.filter_tags(@html_onerror_sample, Pleroma.HTML.Scrubber.TwitterText)
     end
+
+    test "does not allow spans with invalid classes" do
+      expected = """
+      <span>hi</span>
+      """
+
+      assert expected ==
+               HTML.filter_tags(@html_span_class_sample, Pleroma.HTML.Scrubber.TwitterText)
+    end
+
+    test "does allow microformats" do
+      expected = """
+      <span class="h-card"><a class="u-url mention">@<span>foo</span></a></span>
+      """
+
+      assert expected ==
+               HTML.filter_tags(@html_span_microformats_sample, Pleroma.HTML.Scrubber.TwitterText)
+    end
+
+    test "filters invalid microformats markup" do
+      expected = """
+      <span class="h-card"><a>@<span>foo</span></a></span>
+      """
+
+      assert expected ==
+               HTML.filter_tags(
+                 @html_span_invalid_microformats_sample,
+                 Pleroma.HTML.Scrubber.TwitterText
+               )
+    end
   end
 
   describe "default scrubber" do
@@ -80,5 +122,34 @@ defmodule Pleroma.HTMLTest do
 
       assert expected == HTML.filter_tags(@html_onerror_sample, Pleroma.HTML.Scrubber.Default)
     end
+
+    test "does not allow spans with invalid classes" do
+      expected = """
+      <span>hi</span>
+      """
+
+      assert expected == HTML.filter_tags(@html_span_class_sample, Pleroma.HTML.Scrubber.Default)
+    end
+
+    test "does allow microformats" do
+      expected = """
+      <span class="h-card"><a class="u-url mention">@<span>foo</span></a></span>
+      """
+
+      assert expected ==
+               HTML.filter_tags(@html_span_microformats_sample, Pleroma.HTML.Scrubber.Default)
+    end
+
+    test "filters invalid microformats markup" do
+      expected = """
+      <span class="h-card"><a>@<span>foo</span></a></span>
+      """
+
+      assert expected ==
+               HTML.filter_tags(
+                 @html_span_invalid_microformats_sample,
+                 Pleroma.HTML.Scrubber.Default
+               )
+    end
   end
 end