You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
129 lines
4.4 KiB
129 lines
4.4 KiB
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
|
From: "Jason R. Coombs" <jaraco@jaraco.com>
|
|
Date: Mon, 19 Aug 2024 19:28:20 -0400
|
|
Subject: [PATCH] 00436: [CVE-2024-8088] gh-122905: Sanitize names in
|
|
zipfile.Path.
|
|
|
|
Co-authored-by: Jason R. Coombs <jaraco@jaraco.com>
|
|
---
|
|
Lib/test/test_zipfile.py | 17 ++++++
|
|
Lib/zipfile.py | 61 ++++++++++++++++++-
|
|
...-08-11-14-08-04.gh-issue-122905.7tDsxA.rst | 1 +
|
|
3 files changed, 78 insertions(+), 1 deletion(-)
|
|
create mode 100644 Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst
|
|
|
|
diff --git a/Lib/test/test_zipfile.py b/Lib/test/test_zipfile.py
|
|
index 4de6f379a4..8bdc7a1b7d 100644
|
|
--- a/Lib/test/test_zipfile.py
|
|
+++ b/Lib/test/test_zipfile.py
|
|
@@ -3651,6 +3651,23 @@ def test_extract_orig_with_implied_dirs(self, alpharep):
|
|
zipfile.Path(zf)
|
|
zf.extractall(source_path.parent)
|
|
|
|
+ def test_malformed_paths(self):
|
|
+ """
|
|
+ Path should handle malformed paths.
|
|
+ """
|
|
+ data = io.BytesIO()
|
|
+ zf = zipfile.ZipFile(data, "w")
|
|
+ zf.writestr("/one-slash.txt", b"content")
|
|
+ zf.writestr("//two-slash.txt", b"content")
|
|
+ zf.writestr("../parent.txt", b"content")
|
|
+ zf.filename = ''
|
|
+ root = zipfile.Path(zf)
|
|
+ assert list(map(str, root.iterdir())) == [
|
|
+ 'one-slash.txt',
|
|
+ 'two-slash.txt',
|
|
+ 'parent.txt',
|
|
+ ]
|
|
+
|
|
|
|
class EncodedMetadataTests(unittest.TestCase):
|
|
file_names = ['\u4e00', '\u4e8c', '\u4e09'] # Han 'one', 'two', 'three'
|
|
diff --git a/Lib/zipfile.py b/Lib/zipfile.py
|
|
index 86829abce4..b7bf9ef7e3 100644
|
|
--- a/Lib/zipfile.py
|
|
+++ b/Lib/zipfile.py
|
|
@@ -9,6 +9,7 @@
|
|
import itertools
|
|
import os
|
|
import posixpath
|
|
+import re
|
|
import shutil
|
|
import stat
|
|
import struct
|
|
@@ -2243,7 +2244,65 @@ def _difference(minuend, subtrahend):
|
|
return itertools.filterfalse(set(subtrahend).__contains__, minuend)
|
|
|
|
|
|
-class CompleteDirs(ZipFile):
|
|
+class SanitizedNames:
|
|
+ """
|
|
+ ZipFile mix-in to ensure names are sanitized.
|
|
+ """
|
|
+
|
|
+ def namelist(self):
|
|
+ return list(map(self._sanitize, super().namelist()))
|
|
+
|
|
+ @staticmethod
|
|
+ def _sanitize(name):
|
|
+ r"""
|
|
+ Ensure a relative path with posix separators and no dot names.
|
|
+ Modeled after
|
|
+ https://github.com/python/cpython/blob/bcc1be39cb1d04ad9fc0bd1b9193d3972835a57c/Lib/zipfile/__init__.py#L1799-L1813
|
|
+ but provides consistent cross-platform behavior.
|
|
+ >>> san = SanitizedNames._sanitize
|
|
+ >>> san('/foo/bar')
|
|
+ 'foo/bar'
|
|
+ >>> san('//foo.txt')
|
|
+ 'foo.txt'
|
|
+ >>> san('foo/.././bar.txt')
|
|
+ 'foo/bar.txt'
|
|
+ >>> san('foo../.bar.txt')
|
|
+ 'foo../.bar.txt'
|
|
+ >>> san('\\foo\\bar.txt')
|
|
+ 'foo/bar.txt'
|
|
+ >>> san('D:\\foo.txt')
|
|
+ 'D/foo.txt'
|
|
+ >>> san('\\\\server\\share\\file.txt')
|
|
+ 'server/share/file.txt'
|
|
+ >>> san('\\\\?\\GLOBALROOT\\Volume3')
|
|
+ '?/GLOBALROOT/Volume3'
|
|
+ >>> san('\\\\.\\PhysicalDrive1\\root')
|
|
+ 'PhysicalDrive1/root'
|
|
+ Retain any trailing slash.
|
|
+ >>> san('abc/')
|
|
+ 'abc/'
|
|
+ Raises a ValueError if the result is empty.
|
|
+ >>> san('../..')
|
|
+ Traceback (most recent call last):
|
|
+ ...
|
|
+ ValueError: Empty filename
|
|
+ """
|
|
+
|
|
+ def allowed(part):
|
|
+ return part and part not in {'..', '.'}
|
|
+
|
|
+ # Remove the drive letter.
|
|
+ # Don't use ntpath.splitdrive, because that also strips UNC paths
|
|
+ bare = re.sub('^([A-Z]):', r'\1', name, flags=re.IGNORECASE)
|
|
+ clean = bare.replace('\\', '/')
|
|
+ parts = clean.split('/')
|
|
+ joined = '/'.join(filter(allowed, parts))
|
|
+ if not joined:
|
|
+ raise ValueError("Empty filename")
|
|
+ return joined + '/' * name.endswith('/')
|
|
+
|
|
+
|
|
+class CompleteDirs(SanitizedNames, ZipFile):
|
|
"""
|
|
A ZipFile subclass that ensures that implied directories
|
|
are always included in the namelist.
|
|
diff --git a/Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst b/Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst
|
|
new file mode 100644
|
|
index 0000000000..1be44c906c
|
|
--- /dev/null
|
|
+++ b/Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst
|
|
@@ -0,0 +1 @@
|
|
+:class:`zipfile.Path` objects now sanitize names from the zipfile.
|