s3api: Prevent XXE injectionsstable/stein

Previously, clients could use XML external entities (XXEs) to read
arbitrary files from proxy-servers and inject the content into the
request. Since many S3 APIs reflect request content back to the user,
this could be used to extract any secrets that the swift user could
read, such as tempauth credentials, keymaster secrets, etc.

Now, disable entity resolution -- any unknown entities will be replaced
with an empty string. Without resolving the entities, the request is
still processed.

[CVE-2022-47950]

Closes-Bug: #1998625
Co-Authored-By: Romain de Joux <romain.de-joux@ovhcloud.com>
Change-Id: I84494123cfc85e234098c554ecd3e77981f8a096
(cherry picked from commit b8467e190f6fc67fd8fb6a8c5e32b2aa6a10fd8e)

2 files changed, 41 insertions, 1 deletions

diff --git a/swift/common/middleware/s3api/etree.py b/swift/common/middleware/s3api/etree.py
index dcdd7f616..fa4f63b43 100644
--- a/swift/common/middleware/s3api/etree.py
+++ b/swift/common/middleware/s3api/etree.py
@@ -128,7 +128,7 @@ class _Element(lxml.etree.ElementBase):
 
 
 parser_lookup = lxml.etree.ElementDefaultClassLookup(element=_Element)
-parser = lxml.etree.XMLParser()
+parser = lxml.etree.XMLParser(resolve_entities=False, no_network=True)
 parser.set_element_class_lookup(parser_lookup)
 
 Element = parser.makeelement
diff --git a/test/unit/common/middleware/s3api/test_multi_delete.py b/test/unit/common/middleware/s3api/test_multi_delete.py
index c8bb7206f..8042c2bd9 100644
--- a/test/unit/common/middleware/s3api/test_multi_delete.py
+++ b/test/unit/common/middleware/s3api/test_multi_delete.py
@@ -13,6 +13,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+import base64
 import json
 import unittest
 from datetime import datetime
@@ -373,6 +374,45 @@ class TestS3ApiMultiDelete(S3ApiTestCase):
         elem = fromstring(body)
         self.assertEqual(len(elem.findall('Deleted')), len(self.keys))
 
+    def test_object_multi_DELETE_with_system_entity(self):
+        self.keys = ['Key1', 'Key2']
+        self.swift.register(
+            'DELETE', '/v1/AUTH_test/bucket/%s' % self.keys[0],
+            swob.HTTPNotFound, {}, None)
+        self.swift.register(
+            'DELETE', '/v1/AUTH_test/bucket/%s' % self.keys[1],
+            swob.HTTPNoContent, {}, None)
+
+        elem = Element('Delete')
+        for key in self.keys:
+            obj = SubElement(elem, 'Object')
+            SubElement(obj, 'Key').text = key
+        body = tostring(elem, use_s3ns=False)
+        body = body.replace(
+            b'?>\n',
+            b'?>\n<!DOCTYPE foo '
+            b'[<!ENTITY ent SYSTEM "file:///etc/passwd"> ]>\n',
+        ).replace(b'>Key1<', b'>Key1&ent;<')
+        content_md5 = (
+            base64.b64encode(md5(body).digest())
+            .strip())
+
+        req = Request.blank('/bucket?delete',
+                            environ={'REQUEST_METHOD': 'POST'},
+                            headers={
+                                'Authorization': 'AWS test:full_control:hmac',
+                                'Date': self.get_date_header(),
+                                'Content-MD5': content_md5},
+                            body=body)
+        req.date = datetime.now()
+        req.content_type = 'text/plain'
+
+        status, headers, body = self.call_s3api(req)
+        self.assertEqual(status, '200 OK', body)
+        self.assertIn(b'<Deleted><Key>Key2</Key></Deleted>', body)
+        self.assertNotIn(b'root:/root', body)
+        self.assertIn(b'<Deleted><Key>Key1</Key></Deleted>', body)
+
     def _test_no_body(self, use_content_length=False,
                       use_transfer_encoding=False, string_to_md5=''):
         content_md5 = md5(string_to_md5).digest().encode('base64').strip()