From 50efb718b31333051bc2dcb06911b8fa1358c98c Mon Sep 17 00:00:00 2001
From: Shai Berger <shai@platonix.com>
Date: Sat, 11 Oct 2025 21:42:56 +0300
Subject: Fixed CVE-2025-64460 -- Corrected quadratic inner text accumulation
 in XML serializer.

Previously, `getInnerText()` recursively used `list.extend()` on strings,
which added each character from child nodes as a separate list element.
On deeply nested XML content, this caused the overall deserialization
work to grow quadratically with input size, potentially allowing
disproportionate CPU consumption for crafted XML.

The fix separates collection of inner texts from joining them, so that
each subtree is joined only once, reducing the complexity to linear in
the size of the input. These changes also include a mitigation for a
xml.dom.minidom performance issue.

Thanks Seokchan Yoon (https://ch4n3.kr/) for report.

Co-authored-by: Jacob Walls <jacobtylerwalls@gmail.com>
Co-authored-by: Natalia <124304+nessita@users.noreply.github.com>
---
 tests/serializers/test_deserialization.py | 54 +++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

(limited to 'tests')

diff --git a/tests/serializers/test_deserialization.py b/tests/serializers/test_deserialization.py
index 0bbb46b7ce..a718a99038 100644
--- a/tests/serializers/test_deserialization.py
+++ b/tests/serializers/test_deserialization.py
@@ -1,11 +1,15 @@
 import json
+import time
 import unittest
 
 from django.core.serializers.base import DeserializationError, DeserializedObject
 from django.core.serializers.json import Deserializer as JsonDeserializer
 from django.core.serializers.jsonl import Deserializer as JsonlDeserializer
 from django.core.serializers.python import Deserializer
+from django.core.serializers.xml_serializer import Deserializer as XMLDeserializer
+from django.db import models
 from django.test import SimpleTestCase
+from django.test.utils import garbage_collect
 
 from .models import Author
 
@@ -133,3 +137,53 @@ class TestDeserializer(SimpleTestCase):
 
         self.assertEqual(first_item.object, self.jane)
         self.assertEqual(second_item.object, self.joe)
+
+    def test_crafted_xml_performance(self):
+        """The time to process invalid inputs is not quadratic."""
+
+        def build_crafted_xml(depth, leaf_text_len):
+            nested_open = "<nested>" * depth
+            nested_close = "</nested>" * depth
+            leaf = "x" * leaf_text_len
+            field_content = f"{nested_open}{leaf}{nested_close}"
+            return f"""
+                <django-objects version="1.0">
+                   <object model="contenttypes.contenttype" pk="1">
+                      <field name="app_label">{field_content}</field>
+                      <field name="model">m</field>
+                   </object>
+                </django-objects>
+            """
+
+        def deserialize(crafted_xml):
+            iterator = XMLDeserializer(crafted_xml)
+            garbage_collect()
+
+            start_time = time.perf_counter()
+            result = list(iterator)
+            end_time = time.perf_counter()
+
+            self.assertEqual(len(result), 1)
+            self.assertIsInstance(result[0].object, models.Model)
+            return end_time - start_time
+
+        def assertFactor(label, params, factor=2):
+            factors = []
+            prev_time = None
+            for depth, length in params:
+                crafted_xml = build_crafted_xml(depth, length)
+                elapsed = deserialize(crafted_xml)
+                if prev_time is not None:
+                    factors.append(elapsed / prev_time)
+                prev_time = elapsed
+
+            with self.subTest(label):
+                # Assert based on the average factor to reduce test flakiness.
+                self.assertLessEqual(sum(factors) / len(factors), factor)
+
+        assertFactor(
+            "varying depth, varying length",
+            [(50, 2000), (100, 4000), (200, 8000), (400, 16000), (800, 32000)],
+            2,
+        )
+        assertFactor("constant depth, varying length", [(100, 1), (100, 1000)], 2)
-- 
cgit v1.3