首先，跨站腳本攻擊都是由於對用戶的輸入沒有進行嚴格的過濾造成的，所以我們必須在所有數據進入我們的網站和數據庫之前把可能的危險攔截。針對非法的HTML代碼包括單雙引號等，可以使用htmlentities()函數 。
<?php $str = "A "quote" is ＜b＞bold＜/b＞"; // Outputs: A "quote" is bold echo htmlentities($str); // Outputs: A "quote" is bold echo htmlentities($str, ENT_QUOTES); ?> 這樣可以使非法的腳本失效。 但是要注意一點，htmlentities()默認編碼為 ISO-8859-1，如果你的非法腳本編碼為其它，那麼可能無法過濾掉，同時浏覽器卻可以識別和執行。這個問題我先找幾個站點測試後再說。 以下是一個過濾非法腳本的函數,僅供參考： function RemoveXSS($val) { // remove all non-printable characters. CR(0a) and LF(0b) and TAB(9) are allowed // this prevents some character re-spacing such as <javascript> // note that you have to handle splits with , , and 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=@avascript:a& _#X6Cert('XSS')> $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 // @ @ search for the hex values $val = preg_replace("/(&#[x|X]0{0,8}".dechex(ord($search[$i])).";?)/i", $search[$i], $val); // with a ; // @ @ 0{0,7} matches "0" zero to seven times $val = preg_replace("/(�{0,8}".ord($search[$i]).";?)/", $search[$i], $val); // with a ; } // now the only remaining whitespace attacks are , , and $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}([a][b]);?)?"; $pattern .= "|(�{0,8}([10][13]);?)?"; $pattern .= ")?"; } $pattern .= $ra[$i][$j]; } www.2cto.com $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; } } } }
