python3.12/00436-cve-2024-8088-gh-122905-sanitize-names-in-zipfile-path.patch
Charalampos Stratakis e49b43bffa Security fix for CVE-2024-8088
Resolves: RHEL-55939
2024-08-23 16:04:30 +02:00

122 lines
4.3 KiB
Diff

From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: "Miss Islington (bot)"
<31488909+miss-islington@users.noreply.github.com>
Date: Mon, 12 Aug 2024 02:35:17 +0200
Subject: [PATCH] 00436: [CVE-2024-8088] gh-122905: Sanitize names in
zipfile.Path.
---
Lib/test/test_zipfile/_path/test_path.py | 17 +++++
Lib/zipfile/_path/__init__.py | 64 ++++++++++++++++++-
...-08-11-14-08-04.gh-issue-122905.7tDsxA.rst | 1 +
3 files changed, 81 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/_path/test_path.py b/Lib/test/test_zipfile/_path/test_path.py
index 06d5aab69b..90885dbbe3 100644
--- a/Lib/test/test_zipfile/_path/test_path.py
+++ b/Lib/test/test_zipfile/_path/test_path.py
@@ -577,3 +577,20 @@ def test_getinfo_missing(self, alpharep):
zipfile.Path(alpharep)
with self.assertRaises(KeyError):
alpharep.getinfo('does-not-exist')
+
+ 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',
+ ]
diff --git a/Lib/zipfile/_path/__init__.py b/Lib/zipfile/_path/__init__.py
index 78c413563b..42f9fded21 100644
--- a/Lib/zipfile/_path/__init__.py
+++ b/Lib/zipfile/_path/__init__.py
@@ -83,7 +83,69 @@ def __setstate__(self, state):
super().__init__(*args, **kwargs)
-class CompleteDirs(InitializedState, zipfile.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(InitializedState, SanitizedNames, zipfile.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.