Merge pull request #4119 from PHPOffice/powerkiki

Security: prevent XXE (XML External Entity) when loading files

Author: PowerKiKi

CHANGELOG.md

@@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org).
 
 ## TBD - 3.0.0
 
+### Security Fix
+
+- Prevent XXE when loading files
+
 ### Added
 
 - Nothing

src/PhpSpreadsheet/Reader/Security/XmlScanner.php

@@ -35,15 +35,11 @@ private static function forceString(mixed $arg): string
 
     private function toUtf8(string $xml): string
     {
-        $pattern = '/encoding="(.*?)"/';
-        $result = preg_match($pattern, $xml, $matches);
-        $charset = strtoupper($result ? $matches[1] : 'UTF-8');
-
+        $charset = $this->findCharSet($xml);
         if ($charset !== 'UTF-8') {
             $xml = self::forceString(mb_convert_encoding($xml, 'UTF-8', $charset));
 
-            $result = preg_match($pattern, $xml, $matches);
-            $charset = strtoupper($result ? $matches[1] : 'UTF-8');
+            $charset = $this->findCharSet($xml);
             if ($charset !== 'UTF-8') {
                 throw new Reader\Exception('Suspicious Double-encoded XML, spreadsheet file load() aborted to prevent XXE/XEE attacks');
             }
@@ -52,6 +48,22 @@ private function toUtf8(string $xml): string
         return $xml;
     }
 
+    private function findCharSet(string $xml): string
+    {
+        $patterns = [
+            '/encoding="([^"]*]?)"/',
+            "/encoding='([^']*?)'/",
+        ];
+
+        foreach ($patterns as $pattern) {
+            if (preg_match($pattern, $xml, $matches)) {
+                return strtoupper($matches[1]);
+            }
+        }
+
+        return 'UTF-8';
+    }
+
     /**
      * Scan the XML for use of <!ENTITY to prevent XXE/XEE attacks.
      *

tests/data/Reader/Xml/XEETestInvalidUTF-7-single-quote.xml

@@ -0,0 +1,2 @@
+<?xml version="1.0" encoding='UTF-7' standalone="yes"?>
+    +ADw-+ACE-DOCTYPE+ACA-foo+ACA-+AFs-+ADw-+ACE-ENTITY+ACA-toreplace+ACA-+ACI-xxe+AF8-test+ACI-+AD4-+ACA-+AF0-+AD4-+AAo-+ADw-sst+ACA-xmlns+AD0-+ACI-http://schemas.openxmlformats.org/spreadsheetml/2006/main+ACI-+ACA-count+AD0-+ACI-2+ACI-+ACA-uniqueCount+AD0-+ACI-1+ACI-+AD4-+ADw-si+AD4-+ADw-t+AD4-+ACY-toreplace+ADs-+ADw-/t+AD4-+ADw-/si+AD4-+ADw-/sst+AD4-

tests/data/Reader/Xml/XEETestValidUTF-8-single-quote.xml

@@ -0,0 +1,4 @@
+<?xml version='1.0' encoding='UTF-8' standalone='yes'?>
+<root>
+	test: Valid
+</root>