From 2c5ac360e4b9ac04979a2d11dc8e9db93b0741e5 Mon Sep 17 00:00:00 2001
From: Seth Michael Larson <seth@python.org>
Date: Tue, 20 Jan 2026 14:45:58 -0600
Subject: [PATCH] gh-143925: Reject control characters in data: URL mediatypes
 (cherry picked from commit f25509e78e8be6ea73c811ac2b8c928c28841b9f)

Co-authored-by: Seth Michael Larson <seth@python.org>
---
 Lib/test/test_urllib.py                                   | 8 ++++++++
 Lib/urllib/request.py                                     | 5 +++++
 .../2026-01-16-11-51-19.gh-issue-143925.mrtcHW.rst        | 1 +
 3 files changed, 14 insertions(+)
 create mode 100644 Misc/NEWS.d/next/Security/2026-01-16-11-51-19.gh-issue-143925.mrtcHW.rst

diff --git a/Lib/test/test_urllib.py b/Lib/test/test_urllib.py
index ae524c5ffba6b1..2dd739b77b8e4d 100644
--- a/Lib/test/test_urllib.py
+++ b/Lib/test/test_urllib.py
@@ -10,6 +10,7 @@
 from test import support
 from test.support import os_helper
 from test.support import socket_helper
+from test.support import control_characters_c0
 import os
 import socket
 try:
@@ -590,6 +591,13 @@ def test_invalid_base64_data(self):
         # missing padding character
         self.assertRaises(ValueError,urllib.request.urlopen,'data:;base64,Cg=')
 
+    def test_invalid_mediatype(self):
+        for c0 in control_characters_c0():
+            self.assertRaises(ValueError,urllib.request.urlopen,
+                              f'data:text/html;{c0},data')
+        for c0 in control_characters_c0():
+            self.assertRaises(ValueError,urllib.request.urlopen,
+                              f'data:text/html{c0};base64,ZGF0YQ==')
 
 class urlretrieve_FileTests(unittest.TestCase):
     """Test urllib.urlretrieve() on local files"""
diff --git a/Lib/urllib/request.py b/Lib/urllib/request.py
index 566b8087aec277..8d7470a22739ab 100644
--- a/Lib/urllib/request.py
+++ b/Lib/urllib/request.py
@@ -1634,6 +1634,11 @@ def data_open(self, req):
         scheme, data = url.split(":",1)
         mediatype, data = data.split(",",1)
 
+        # Disallow control characters within mediatype.
+        if re.search(r"[\x00-\x1F\x7F]", mediatype):
+            raise ValueError(
+                "Control characters not allowed in data: mediatype")
+
         # even base64 encoded data URLs might be quoted so unquote in any case:
         data = unquote_to_bytes(data)
         if mediatype.endswith(";base64"):
diff --git a/Misc/NEWS.d/next/Security/2026-01-16-11-51-19.gh-issue-143925.mrtcHW.rst b/Misc/NEWS.d/next/Security/2026-01-16-11-51-19.gh-issue-143925.mrtcHW.rst
new file mode 100644
index 00000000000000..46109dfbef3ee7
--- /dev/null
+++ b/Misc/NEWS.d/next/Security/2026-01-16-11-51-19.gh-issue-143925.mrtcHW.rst
@@ -0,0 +1 @@
+Reject control characters in ``data:`` URL media types.