[pmg-devel] [PATCH pmg-api v2] fix #3734: scrub 'url' from style tags/attributes

[Dominik Csapak]

if 'view images' for the quarantine is disabled, it is expected that
*no* images will be loaded. but in addition to img (src/href/etc.)
also css can load external images via the 'url' directive

since html scrubber does not parse/iterate over css, we simply remove
the url+protocol part of those tags/attributes. this technically leaves behind
invalid css, but the browsers should cope with that.
(we cannot 'cleanly' remove without much more effort because of quoting)

also we have to scrub the style tags in 'dump_html' since HTML::Scrubber
does not have a way to modify the *content* of a tag, only the
attributes...

Signed-off-by: Dominik Csapak <d.csapak at proxmox.com>
---
changes from v1:
* replace url with ___ and protocol:// with _ instead of removing
* move sub out and use the reference
* always pass $cid_hash and only use it in the function when
  $view_images is set
* improve comment to show what 'dump_html' does

@thomas: a note to our off-list discussion regarding url-encoding the
protocol: you *could* do it, but the browser does not recognize it as
a protocol and interprets it as a relative url, so we're safe on
this regard

 src/PMG/HTMLMail.pm | 31 +++++++++++++++++++++++++++----
 1 file changed, 27 insertions(+), 4 deletions(-)

diff --git a/src/PMG/HTMLMail.pm b/src/PMG/HTMLMail.pm
index b69a596..c5c94bf 100644
--- a/src/PMG/HTMLMail.pm
+++ b/src/PMG/HTMLMail.pm
@@ -15,8 +15,26 @@ use HTML::Scrubber;
 use PMG::Utils;
 use PMG::MIMEUtils;
 
+# $value is a ref to a string scalar
+my sub remove_urls {
+    my ($value) = @_;
+    # convert 'url([..])' to '___([..])' so the browser does not load it
+    $$value =~ s|url\(|___(|gi;
+
+    # similar for all protocols
+    $$value =~ s|[a-z0-9]+://|_|gi;
+}
+
+my sub remove_urls_from_attr {
+    my ($obj, $tag_name, $attr_name, $value) = @_;
+
+    remove_urls(\$value);
+
+    return $value;
+}
+
 sub dump_html {
-    my ($tree, $cid_hash) = @_;
+    my ($tree, $cid_hash, $view_images) = @_;
 
     my @html = ();
 
@@ -31,7 +49,7 @@ sub dump_html {
 		# try to open a new window when user activates a anchor
 		$node->{target} = '_blank' if $tag eq 'a';
 
-		if ($tag eq 'img') {
+		if ($tag eq 'img' && $view_images) {
 		    if ($node->{src} && $node->{src} =~ m/^cid:(\S+)$/) {
 			if (my $datauri = $cid_hash->{$1}) {
 			    $node->{src} = $datauri;
@@ -39,6 +57,10 @@ sub dump_html {
 		    }
 		}
 
+		if ($tag eq 'style' && !$view_images) {
+		    remove_urls($_) for grep { !ref $$_ } $node->content_refs_list();
+		}
+
 		if($start) { # on the way in
 		    push(@html, $node->starttag);
 		} else {
@@ -137,7 +159,7 @@ sub getscrubber {
 	    span => 1,
 	    src => $viewimages ? qr{^(?!(?:java)?script)}i : 0,
 	    start => 1,
-	    style => 1,
+	    style => $viewimages ? 1 : \remove_urls_from_attr,
 	    summary => 1,
 	    tabindex => 1,
 	    target => 1,
@@ -267,7 +289,8 @@ sub entity_to_html {
 	$tree->parse($raw);
 	$tree->eof();
 
-	my $whtml = dump_html($tree, $viewimages ? $cid_hash : {});
+	# normalizes html, replaces CID references with data uris and scrubs style tags
+	my $whtml = dump_html($tree, $cid_hash, $viewimages);
 	$tree->delete;
 
 	# remove dangerous/unneeded elements
-- 
2.30.2