From: Seth Michael Larson <seth@python.org>
Date: Sun, 25 Jan 2026 17:05:57 +0000 (-0600)
Subject: [3.12] gh-143925: Reject control characters in data: URL mediatypes (#144113)
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=4ed11d3cd288e6b90196a15c5a825a45d318fe47;p=thirdparty%2FPython%2Fcpython.git

[3.12] gh-143925: Reject control characters in data: URL mediatypes (#144113)

* [3.12] gh-143925: Reject control characters in data: URL mediatypes
(cherry picked from commit f25509e78e8be6ea73c811ac2b8c928c28841b9f)
(cherry picked from commit 2c9c746077d8119b5bcf5142316992e464594946)

Co-authored-by: Seth Michael Larson <seth@python.org>

* Remove "ExtraAssertations"
---

diff --git a/Lib/test/test_urllib.py b/Lib/test/test_urllib.py
index 9becb72c7415..0d46a455664b 100644
--- a/Lib/test/test_urllib.py
+++ b/Lib/test/test_urllib.py
@@ -12,6 +12,7 @@ from test import support
 from test.support import os_helper
 from test.support import socket_helper
 from test.support import warnings_helper
+from test.support import control_characters_c0
 import os
 try:
     import ssl
@@ -688,6 +689,13 @@ class urlopen_DataTests(unittest.TestCase):
         # 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 c7ded0f67fc6..16449d6ff719 100644
--- a/Lib/urllib/request.py
+++ b/Lib/urllib/request.py
@@ -1655,6 +1655,11 @@ class DataHandler(BaseHandler):
         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 000000000000..46109dfbef3e
--- /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.