python · pablogsal · Jan 25, 2026 · Jan 20, 2026 · Jan 21, 2026
diff --git a/Lib/test/test_urllib.py b/Lib/test/test_urllib.py
@@ -12,6 +12,7 @@
 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 @@ 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
@@ -1655,6 +1655,11 @@ 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
@@ -0,0 +1 @@
+Reject control characters in ``data:`` URL media types.
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		Reject control characters in ``data:`` URL media types.