Created
November 17, 2013 05:30
-
-
Save ken-muturi/7509684 to your computer and use it in GitHub Desktop.
XSS Clean
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| public static function xss_clean($array) | |
| { | |
| foreach ($array as $key => $data) { | |
| if (is_array($data)) { | |
| $array[$key] = self::xss_clean($data); | |
| } else { | |
| $array[$key] = self::do_xss_clean($data); | |
| } | |
| } | |
| return $array; | |
| } | |
| public static function do_xss_clean($data) | |
| { | |
| // Fix &entity\n; | |
| $data = str_replace(array('&','<','>'), array('&amp;','&lt;','&gt;'), $data); | |
| $data = preg_replace('/(&#*\w+)[\x00-\x20]+;/u', '$1;', $data); | |
| $data = preg_replace('/(&#x*[0-9A-F]+);*/iu', '$1;', $data); | |
| $data = html_entity_decode($data, ENT_COMPAT, 'UTF-8'); | |
| // Remove any attribute starting with "on" or xmlns | |
| $data = preg_replace('#(<[^>]+?[\x00-\x20"\'])(?:on|xmlns)[^>]*+>#iu', '$1>', $data); | |
| // Remove javascript: and vbscript: protocols | |
| $data = preg_replace('#([a-z]*)[\x00-\x20]*=[\x00-\x20]*([`\'"]*)[\x00-\x20]*j[\x00-\x20]*a[\x00-\x20]*v[\x00-\x20]*a[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iu', '$1=$2nojavascript...', $data); | |
| $data = preg_replace('#([a-z]*)[\x00-\x20]*=([\'"]*)[\x00-\x20]*v[\x00-\x20]*b[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iu', '$1=$2novbscript...', $data); | |
| $data = preg_replace('#([a-z]*)[\x00-\x20]*=([\'"]*)[\x00-\x20]*-moz-binding[\x00-\x20]*:#u', '$1=$2nomozbinding...', $data); | |
| // Only works in IE: <span style="width: expression(alert('Ping!'));"></span> | |
| $data = preg_replace('#(<[^>]+?)style[\x00-\x20]*=[\x00-\x20]*[`\'"]*.*?expression[\x00-\x20]*\([^>]*+>#i', '$1>', $data); | |
| $data = preg_replace('#(<[^>]+?)style[\x00-\x20]*=[\x00-\x20]*[`\'"]*.*?behaviour[\x00-\x20]*\([^>]*+>#i', '$1>', $data); | |
| $data = preg_replace('#(<[^>]+?)style[\x00-\x20]*=[\x00-\x20]*[`\'"]*.*?s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:*[^>]*+>#iu', '$1>', $data); | |
| // Remove namespaced elements (we do not need them) | |
| $data = preg_replace('#</*\w+:\w[^>]*+>#i', '', $data); | |
| do | |
| { | |
| // Remove really unwanted tags | |
| $old_data = $data; | |
| $data = preg_replace('#</*(?:applet|b(?:ase|gsound|link)|(?:set)?|i(?:frame|layer)|l(?:ayer|ink)|meta|object|s(?:cript|tyle)|title|xml)[^>]*+>#i', '', $data); | |
| } | |
| while ($old_data !== $data); | |
| // we are done... | |
| return $data; | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment