https://github.com/python/cpython/commit/f25509e78e8be6ea73c811ac2b8c928c28841b9f
commit: f25509e78e8be6ea73c811ac2b8c928c28841b9f
branch: main
author: Seth Michael Larson <[email protected]>
committer: sethmlarson <[email protected]>
date: 2026-01-20T20:45:58Z
summary:
gh-143925: Reject control characters in data: URL mediatypes
files:
A Misc/NEWS.d/next/Security/2026-01-16-11-51-19.gh-issue-143925.mrtcHW.rst
M Lib/test/test_urllib.py
M Lib/urllib/request.py
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 f32de189b1353a..f5f17f223a4585 100644
--- a/Lib/urllib/request.py
+++ b/Lib/urllib/request.py
@@ -1636,6 +1636,11 @@ 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.
_______________________________________________
Python-checkins mailing list -- [email protected]
To unsubscribe send an email to [email protected]
https://mail.python.org/mailman3//lists/python-checkins.python.org
Member address: [email protected]
