PHP和XSS跨站攻击

                                                                       作者:Haohappy2004 的 Blog

        其实这个话题很早就想说说了，发现国内不少PHP站点都有XSS漏洞。今天偶然看到PHP5的一个XSS漏洞，在此小结一下。顺便提醒，使用PHP5的朋友最好打下补丁，或者升级一下。

如果你不懂什么是XSS，可以看这里，或者这里（中文的也许会好懂一些）。

国内不少论坛都存在跨站脚本漏洞，例如这里  有一个Google Hack+XSS的攻击例子，针对的是Discuz 4.0.0RC3。国外也很多这样的例子，甚至Google也出现过，不过在12月初时修正了。跨站攻击很容易就可以构造，而且非常隐蔽，不易被查觉（通常盗取信息后马上跳转回原页面）。
如何攻击，在此不作说明（也不要问我），主要谈谈如何防范。首先，跨站脚本攻击都是由于对用户的输入没有进行严格的过滤造成的，所以我们必须在所有数据进入我们的网站和数据库之前把可能的危险拦截。针对非法的HTML代码包括单双引号等，可以使用<defanged-span style="COLOR: rgb(0,0,187)"></defanged-span>htmlentities() 。

<?php
$str = "A ''''quote'''' is <b>bold</b>";

// Outputs: A ''''quote'''' is &lt;b&gt;bold&lt;/b&gt;
echo htmlentities($str);

// Outputs: A &#039;quote&#039; is &lt;b&gt;bold&lt;/b&gt;
echo htmlentities($str, ENT_QUOTES);
?>


这样可以使非法的脚本失效。
 
<defanged-span style="COLOR: rgb(0,119,0)"></defanged-span>但是要注意一点，htmlentities()默认编码为 ISO-8859-1，如果你的非法脚本编码为其它，那么可能无法过滤掉，同时浏览器却可以识别和执行。这个问题我先找几个站点测试后再说。

这里提供一个过滤非法脚本的函数：

function RemoveXSS($val) {
   // remove all non-printable characters. CR(0a) and LF(0b) and TAB(9) are allowed
   // this prevents some character re-spacing such as <java\0script>
   // note that you have to handle splits with \n, \r, and \t later since they *are* allowed in some inputs
   $val = preg_replace(''''/([\x00-\x08][\x0b-\x0c][\x0e-\x20])/'''', '''''''', $val);
   
   // straight replacements, the user should never need these since they''''re normal characters
   // this prevents like <IMG SRC=&#X40&#X61&#X76&#X61&#X73&#X63&#X72&#X69&#X70&#X74&#X3A&#X61&#X6C&#X65&#X72&#X74&#X28&#X27&#X58&#X53&#X53&#X27&#X29>
   $search = ''''abcdefghijklmnopqrstuvwxyz'''';
   $search .= ''''ABCDEFGHIJKLMNOPQRSTUVWXYZ'''';
   $search .= ''''1234567890!@#$%^&*()'''';
   $search .= ''''~`";:?+/={}[]-_|\''''\\'''';
   for ($i = 0; $i < strlen($search); $i++) {
      // ;? matches the ;, which is optional
      // 0{0,7} matches any padded zeros, which are optional and go up to 8 chars
   
      // &#x0040 @ search for the hex values
      $val = preg_replace(''''/(&#[x|X]0{0,8}''''.dechex(ord($search[$i])).'''';?)/i'''', $search[$i], $val); // with a ;
      // &#00064 @ 0{0,7} matches ''''0'''' zero to seven times
      $val = preg_replace(''''/(&#0{0,8}''''.ord($search[$i]).'''';?)/'''', $search[$i], $val); // with a ;
   }
   
   // now the only remaining whitespace attacks are \t, \n, and \r
   $ra1 = Array(''''javascript'''', ''''vbscript'''', ''''expression'''', ''''applet'''', ''''meta'''', ''''xml'''', ''''blink'''', ''''link'''', ''''style'''', ''''script'''', ''''embed'''', ''''object'''', ''''iframe'''', ''''frame'''', ''''frameset'''', ''''ilayer'''', ''''layer'''', ''''bgsound'''', ''''title'''', ''''base'''');
   $ra2 = Array(''''onabort'''', ''''onactivate'''', ''''onafterprint'''', ''''onafterupdate'''', ''''onbeforeactivate'''', ''''onbeforecopy'''', ''''onbeforecut'''', ''''onbeforedeactivate'''', ''''onbeforeeditfocus'''', ''''onbeforepaste'''', ''''onbeforeprint'''', ''''onbeforeunload'''', ''''onbeforeupdate'''', ''''onblur'''', ''''onbounce'''', ''''oncellchange'''', ''''onchange'''', ''''onclick'''', ''''oncontextmenu'''', ''''oncontrolselect'''', ''''oncopy'''', ''''oncut'''', ''''ondataavailable'''', ''''ondatasetchanged'''', ''''ondatasetcomplete'''', ''''ondblclick'''', ''''ondeactivate'''', ''''ondrag'''', ''''ondragend'''', ''''ondragenter'''', ''''ondragleave'''', ''''ondragover'''', ''''ondragstart'''', ''''ondrop'''', ''''onerror'''', ''''onerrorupdate'''', ''''onfilterchange'''', ''''onfinish'''', ''''onfocus'''', ''''onfocusin'''', ''''onfocusout'''', ''''onhelp'''', ''''onkeydown'''', ''''onkeypress'''', ''''onkeyup'''', ''''onlayoutcomplete'''', ''''onload'''', ''''onlosecapture'''', ''''onmousedown'''', ''''onmouseenter'''', ''''onmouseleave'''', ''''onmousemove'''', ''''onmouseout'''', ''''onmouseover'''', ''''onmouseup'''', ''''onmousewheel'''', ''''onmove'''', ''''onmoveend'''', ''''onmovestart'''', ''''onpaste'''', ''''onpropertychange'''', ''''onreadystatechange'''', ''''onreset'''', ''''onresize'''', ''''onresizeend'''', ''''onresizestart'''', ''''onrowenter'''', ''''onrowexit'''', ''''onrowsdelete'''', ''''onrowsinserted'''', ''''onscroll'''', ''''onselect'''', ''''onselectionchange'''', ''''onselectstart'''', ''''onstart'''', ''''onstop'''', ''''onsubmit'''', ''''onunload'''');
   $ra = array_merge($ra1, $ra2);
   
   $found = true; // keep replacing as long as the previous round replaced something
   while ($found == true) {
      $val_before = $val;
      for ($i = 0; $i < sizeof($ra); $i++) {
         $pattern = ''''/'''';
         for ($j = 0; $j < strlen($ra[$i]); $j++) {
            if ($j > 0) {
               $pattern .= ''''('''';
               $pattern .= ''''(&#[x|X]0{0,8}([9][a][b]);?)?'''';
               $pattern .= ''''|(&#0{0,8}([9][10][13]);?)?'''';
               $pattern .= '''')?'''';
            }
            $pattern .= $ra[$i][$j];
         }
         $pattern .= ''''/i'''';
         $replacement = substr($ra[$i], 0, 2).''''<x>''''.substr($ra[$i], 2); // add in <> to nerf the tag
         $val = preg_replace($pattern, $replacement, $val); // filter out the hex tags
         if ($val_before == $val) {
            // no replacements were made, so exit the loop
            $found = false;
         }
      }
   }
}

<noscript src="http://www.google-analytics.com/urchin.js" type="text/javascript"> </noscript> <noscript type="text/javascript"> _uacct = "UA-260914-1"; urchinTracker(); </noscript>