Fix #181: Arbitrary file write during tarfile extraction

.changes/unreleased/Security-20240808-154439.yaml

@@ -0,0 +1,6 @@
+kind: Security
+body: Fix arbitrary file write during tarfile extraction
+time: 2024-08-08T15:44:39.601346-05:00
+custom:
+    Author: aranke
+    PR: "182"

dbt_common/clients/system.py

@@ -608,11 +608,35 @@ def rename(from_path: str, to_path: str, force: bool = False) -> None:
     shutil.move(from_path, to_path)
 
 
+def safe_extract(tarball, path=".", members=None, *, numeric_owner=False):
+    """
+    Fix for CWE-22: CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
+    Solution copied from https://github.com/mindsdb/mindsdb/blob/main/mindsdb/utilities/fs.py
+    """
+
+    def _is_within_directory(directory, target):
+        abs_directory = os.path.abspath(directory)
+        abs_target = os.path.abspath(target)
+        prefix = os.path.commonprefix([abs_directory, abs_target])
+        return prefix == abs_directory
+
+    # for py >= 3.12
+    if hasattr(tarball, "data_filter"):
+        tarball.extractall(path, members=members, numeric_owner=numeric_owner, filter="data")
+    else:
+        for member in tarball.getmembers():
+            member_path = os.path.join(path, member.name)
+            if not _is_within_directory(path, member_path):
+                raise tarfile.OutsideDestinationError(member, path)
+
+        tarball.extractall(path, members=members, numeric_owner=numeric_owner)
+
+
 def untar_package(tar_path: str, dest_dir: str, rename_to: Optional[str] = None) -> None:
     tar_path = convert_path(tar_path)
     tar_dir_name = None
     with tarfile.open(tar_path, "r:gz") as tarball:
-        tarball.extractall(dest_dir)
+        safe_extract(tarball, dest_dir)
         tar_dir_name = os.path.commonprefix(tarball.getnames())
     if rename_to:
         downloaded_path = os.path.join(dest_dir, tar_dir_name)

tests/unit/test_system_client.py

@@ -268,3 +268,18 @@ def test_untar_package_empty(self) -> None:
             with self.assertRaises(tarfile.ReadError) as exc:
                 dbt_common.clients.system.untar_package(named_file.name, self.tempdest)
             self.assertEqual("empty file", str(exc.exception))
+
+    def test_untar_package_outside_directory(self) -> None:
+        with NamedTemporaryFile(
+            prefix="my-package.2", suffix=".tar.gz", dir=self.tempdir, delete=False
+        ) as named_tar_file:
+            tar_file_full_path = named_tar_file.name
+            with NamedTemporaryFile(prefix="a", suffix=".txt", dir=self.tempdir) as file_a:
+                file_a.write(b"some text in the text file")
+                relative_file_a = "/../" + os.path.basename(file_a.name)
+                with tarfile.open(fileobj=named_tar_file, mode="w:gz") as tar:
+                    tar.addfile(tarfile.TarInfo(relative_file_a), open(file_a.name))
+
+        assert tarfile.is_tarfile(tar.name)
+        with self.assertRaises(tarfile.OutsideDestinationError):
+            dbt_common.clients.system.untar_package(tar_file_full_path, self.tempdest)