[CVE-2022-25236]lib: Protect against insertion of namesep characters into namespace...

lib: Protect against malicious namespace declarations
lib: Fix (harmless) use of uninitialized memory

Change-Id: I7e8163e93fad8dd0a5877a4c61de2fc5aba75e16

diff --git a/lib/xmlparse.c b/lib/xmlparse.c
index 5ba56ea..2e4b198 100644 (file)
--- a/lib/xmlparse.c
+++ b/lib/xmlparse.c
@@ -716,8 +716,7 @@ XML_ParserCreate(const XML_Char *encodingName) {
 
 XML_Parser XMLCALL
 XML_ParserCreateNS(const XML_Char *encodingName, XML_Char nsSep) {
-  XML_Char tmp[2];
-  *tmp = nsSep;
+  XML_Char tmp[2] = {nsSep, 0};
   return XML_ParserCreate_MM(encodingName, NULL, tmp);
 }
 
@@ -1342,8 +1341,7 @@ XML_ExternalEntityParserCreate(XML_Parser oldParser, const XML_Char *context,
      would be otherwise.
   */
   if (parser->m_ns) {
-    XML_Char tmp[2];
-    *tmp = parser->m_namespaceSeparator;
+    XML_Char tmp[2] = {parser->m_namespaceSeparator, 0};
     parser = parserCreate(encodingName, &parser->m_mem, tmp, newDtd);
   } else {
     parser = parserCreate(encodingName, &parser->m_mem, NULL, newDtd);
@@ -3664,6 +3662,17 @@ addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId,
     if (! mustBeXML && isXMLNS
         && (len > xmlnsLen || uri[len] != xmlnsNamespace[len]))
       isXMLNS = XML_FALSE;
+
+    // NOTE: While Expat does not validate namespace URIs against RFC 3986,
+    //       we have to at least make sure that the XML processor on top of
+    //       Expat (that is splitting tag names by namespace separator into
+    //       2- or 3-tuples (uri-local or uri-local-prefix)) cannot be confused
+    //       by an attacker putting additional namespace separator characters
+    //       into namespace declarations.  That would be ambiguous and not to
+    //       be expected.
+    if (parser->m_ns && (uri[len] == parser->m_namespaceSeparator)) {
+      return XML_ERROR_SYNTAX;
+    }
   }
   isXML = isXML && len == xmlLen;
   isXMLNS = isXMLNS && len == xmlnsLen;