From 735bb985a202d0e0c38b6335159c17ec427b522b Mon Sep 17 00:00:00 2001
From: Aaron Patterson <aaron.patterson@gmail.com>
Date: Fri, 15 Mar 2013 15:04:00 -0700
Subject: [PATCH] fix protocol checking in sanitization [CVE-2013-1857]

Conflicts:
	actionpack/lib/action_controller/vendor/html-scanner/html/sanitizer.rb
---
 .../action_controller/vendor/html-scanner/html/sanitizer.rb    |  4 ++--
 actionpack/test/template/html-scanner/sanitizer_test.rb        | 10 ++++++++++
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/actionpack/lib/action_controller/vendor/html-scanner/html/sanitizer.rb b/actionpack/lib/action_controller/vendor/html-scanner/html/sanitizer.rb
index 204e86f..57f05d8 100644
--- a/actionpack/lib/action_controller/vendor/html-scanner/html/sanitizer.rb
+++ b/actionpack/lib/action_controller/vendor/html-scanner/html/sanitizer.rb
@@ -66,7 +66,7 @@ module HTML
 
     # A regular expression of the valid characters used to separate protocols like
     # the ':' in 'http://foo.com'
-    self.protocol_separator     = /:|(&#0*58)|(&#x70)|(%|&#37;)3A/
+    self.protocol_separator     = /:|(&#0*58)|(&#x70)|(&#x0*3a)|(%|&#37;)3A/i
 
     # Specifies a Set of HTML attributes that can have URIs.
     self.uri_attributes         = Set.new(%w(href src cite action longdesc xlink:href lowsrc))
@@ -171,7 +171,7 @@ module HTML
 
     def contains_bad_protocols?(attr_name, value)
       uri_attributes.include?(attr_name) &&
-      (value =~ /(^[^\/:]*):|(&#0*58)|(&#x70)|(%|&#37;)3A/ && !allowed_protocols.include?(value.split(protocol_separator).first.downcase))
+      (value =~ /(^[^\/:]*):|(&#0*58)|(&#x70)|(&#x0*3a)|(%|&#37;)3A/i && !allowed_protocols.include?(value.split(protocol_separator).first.downcase.strip))
     end
   end
 end
diff --git a/actionpack/test/template/html-scanner/sanitizer_test.rb b/actionpack/test/template/html-scanner/sanitizer_test.rb
index ee3a52d..e9dc1e6 100644
--- a/actionpack/test/template/html-scanner/sanitizer_test.rb
+++ b/actionpack/test/template/html-scanner/sanitizer_test.rb
@@ -176,6 +176,7 @@ class SanitizerTest < ActionController::TestCase
    %(<IMG SRC="jav&#x0A;ascript:alert('XSS');">),
    %(<IMG SRC="jav&#x0D;ascript:alert('XSS');">),
    %(<IMG SRC=" &#14;  javascript:alert('XSS');">),
+   %(<IMG SRC="javascript&#x3a;alert('XSS');">),
    %(<IMG SRC=`javascript:alert("RSnake says, 'XSS'")`>)].each_with_index do |img_hack, i|
     define_method "test_should_not_fall_for_xss_image_hack_#{i+1}" do
       assert_sanitized img_hack, "<img>"
@@ -281,6 +282,15 @@ class SanitizerTest < ActionController::TestCase
     assert_sanitized "<span class=\"\\", "<span class=\"\\\">"
   end
 
+  def test_x03a
+    assert_sanitized %(<a href="javascript&#x3a;alert('XSS');">), "<a>"
+    assert_sanitized %(<a href="javascript&#x003a;alert('XSS');">), "<a>"
+    assert_sanitized %(<a href="http&#x3a;//legit">), %(<a href="http://legit">)
+    assert_sanitized %(<a href="javascript&#x3A;alert('XSS');">), "<a>"
+    assert_sanitized %(<a href="javascript&#x003A;alert('XSS');">), "<a>"
+    assert_sanitized %(<a href="http&#x3A;//legit">), %(<a href="http://legit">)
+  end
+
 protected
   def assert_sanitized(input, expected = nil)
     @sanitizer ||= HTML::WhiteListSanitizer.new
-- 
1.8.1.1