gitweb: Introduce esc_attr to escape attributes of HTML elements

It is needed only to escape attributes of handcrafted HTML elements,
and not those generated using CGI.pm subroutines / methods for HTML
generation.

While at it, add esc_url and esc_html where needed, and prefer to use
CGI.pm HTML generating methods than handcrafted HTML code.  Most of
those are probably unnecessary (could be exploited only by person with
write access to gitweb config, or at least access to the repository).

This fixes CVE-2010-3906

Reported-by: Emanuele Gentili <redacted>
Helped-by: John 'Warthog9' Hawley <redacted>
Helped-by: Jonathan Nieder <redacted>
Signed-off-by: Jakub Narebski <redacted>
Signed-off-by: Junio C Hamano <redacted>

diff --git a/gitweb.perl b/gitweb.perl
index 0d38bd1fd0596d620673048123e174a75c5be827795aced5035fc1c0351adb0a..f20bdbf70338ef192e102ebf983f95a048f192acdcc4c7f1a221f5f1375a2df9 100755 (executable)
--- a/gitweb.perl
+++ b/gitweb.perl
@@ -1416,6 +1416,13 @@ sub esc_url {
        return $str;
 }
 
+# quote unsafe characters in HTML attributes
+sub esc_attr {
+
+       # for XHTML conformance escaping '"' to '"' is not enough
+       return esc_html(@_);
+}
+
 # replace invalid utf8 character with SUBSTITUTION sequence
 sub esc_html {
        my $str = shift;
@@ -1821,7 +1828,7 @@ sub format_ref_marker {
                                        hash=>$dest
                                )}, $name);
 
-                       $markers .= " <span class=\"$class\" title=\"$ref\">" .
+                       $markers .= " <span class=\"".esc_attr($class)."\" title=\"".esc_attr($ref)."\">" .
                                $link . "</span>";
                }
        }
@@ -1905,7 +1912,7 @@ sub git_get_avatar {
                return $pre_white .
                       "<img width=\"$size\" " .
                            "class=\"avatar\" " .
-                           "src=\"$url\" " .
+                           "src=\"".esc_url($url)."\" " .
                            "alt=\"\" " .
                       "/>" . $post_white;
        } else {
@@ -2616,7 +2623,7 @@ sub git_show_project_tagcloud {
        } else {
                my @tags = sort { $cloud->{$a}->{count} <=> $cloud->{$b}->{count} } keys %$cloud;
                return '<p align="center">' . join (', ', map {
-                       "<a href=\"$home_link?by_tag=$_\">$cloud->{$_}->{topname}</a>"
+                       $cgi->a({-href=>"$home_link?by_tag=$_"}, $cloud->{$_}->{topname})
                } splice(@tags, 0, $count)) . '</p>';
        }
 }
@@ -3530,11 +3537,11 @@ EOF
        # print out each stylesheet that exist, providing backwards capability
        # for those people who defined $stylesheet in a config file
        if (defined $stylesheet) {
-               print '<link rel="stylesheet" type="text/css" href="'.$stylesheet.'"/>'."\n";
+               print '<link rel="stylesheet" type="text/css" href="'.esc_url($stylesheet).'"/>'."\n";
        } else {
                foreach my $stylesheet (@stylesheets) {
                        next unless $stylesheet;
-                       print '<link rel="stylesheet" type="text/css" href="'.$stylesheet.'"/>'."\n";
+                       print '<link rel="stylesheet" type="text/css" href="'.esc_url($stylesheet).'"/>'."\n";
                }
        }
        if (defined $project) {
@@ -3547,7 +3554,7 @@ EOF
                        my $type = lc($format);
                        my %link_attr = (
                                '-rel' => 'alternate',
-                               '-title' => "$project - $href_params{'-title'} - $format feed",
+                               '-title' => esc_attr("$project - $href_params{'-title'} - $format feed"),
                                '-type' => "application/$type+xml"
                        );
 
@@ -3574,13 +3581,13 @@ EOF
        } else {
                printf('<link rel="alternate" title="%s projects list" '.
                       'href="%s" type="text/plain; charset=utf-8" />'."\n",
-                      $site_name, href(project=>undef, action=>"project_index"));
+                      esc_attr($site_name), href(project=>undef, action=>"project_index"));
                printf('<link rel="alternate" title="%s projects feeds" '.
                       'href="%s" type="text/x-opml" />'."\n",
-                      $site_name, href(project=>undef, action=>"opml"));
+                      esc_attr($site_name), href(project=>undef, action=>"opml"));
        }
        if (defined $favicon) {
-               print qq(<link rel="shortcut icon" href="$favicon" type="image/png" />\n);
+               print qq(<link rel="shortcut icon" href=").esc_url($favicon).qq(" type="image/png" />\n);
        }
 
        print "</head>\n" .
@@ -3593,7 +3600,7 @@ EOF
        print "<div class=\"page_header\">\n" .
              $cgi->a({-href => esc_url($logo_url),
                       -title => $logo_label},
-                     qq(<img src="$logo" width="72" height="27" alt="git" class="logo"/>));
+                     qq(<img src=").esc_url($logo).qq(" width="72" height="27" alt="git" class="logo"/>));
        print $cgi->a({-href => esc_url($home_link)}, $home_link_str) . " / ";
        if (defined $project) {
                print $cgi->a({-href => href(action=>"summary")}, esc_html($project));
@@ -3699,7 +3706,7 @@ sub git_footer_html {
                insert_file($site_footer);
        }
 
-       print qq!<script type="text/javascript" src="$javascript"></script>\n!;
+       print qq!<script type="text/javascript" src="!.esc_url($javascript).qq!"></script>\n!;
        if (defined $action &&
            $action eq 'blame_incremental') {
                print qq!<script type="text/javascript">\n!.
@@ -5910,14 +5917,14 @@ sub git_blob {
        } else {
                print "<div class=\"page_nav\">\n" .
                      "<br/><br/></div>\n" .
-                     "<div class=\"title\">$hash</div>\n";
+                     "<div class=\"title\">".esc_html($hash)."</div>\n";
        }
        git_print_page_path($file_name, "blob", $hash_base);
        print "<div class=\"page_body\">\n";
        if ($mimetype =~ m!^image/!) {
-               print qq!<img type="$mimetype"!;
+               print qq!<img type="!.esc_attr($mimetype).qq!"!;
                if ($file_name) {
-                       print qq! alt="$file_name" title="$file_name"!;
+                       print qq! alt="!.esc_attr($file_name).qq!" title="!.esc_attr($file_name).qq!"!;
                }
                print qq! src="! .
                      href(action=>"blob_plain", hash=>$hash,
@@ -5992,7 +5999,7 @@ sub git_tree {
                undef $hash_base;
                print "<div class=\"page_nav\">\n";
                print "<br/><br/></div>\n";
-               print "<div class=\"title\">$hash</div>\n";
+               print "<div class=\"title\">".esc_html($hash)."</div>\n";
        }
        if (defined $file_name) {
                $basedir = $file_name;
@@ -6460,7 +6467,7 @@ sub git_blobdiff {
                        git_print_header_div('commit', esc_html($co{'title'}), $hash_base);
                } else {
                        print "<div class=\"page_nav\"><br/>$formats_nav<br/></div>\n";
-                       print "<div class=\"title\">$hash vs $hash_parent</div>\n";
+                       print "<div class=\"title\">".esc_html("$hash vs $hash_parent")."</div>\n";
                }
                if (defined $file_name) {
                        git_print_page_path($file_name, "blob", $hash_base);