Adding tarfile member sanitization to extractall() (#1709)

Fix a widespread bug named CVE-2007-4559, which is a 15 year old bug
in the Python tarfile package. By using extract() or extractall() on a tarfile
object without sanitizing input, a maliciously crafted .tar file could
perform a directory path traversal attack. This patch essentially checks to
see if all tarfile members will be extracted safely and throws an exception
otherwise.

test-tools/build-wasi-sdk/build_wasi_sdk.py

@@ -111,7 +111,26 @@ def unpack(tar_file, strip_prefix, dest_dir):
     with tempfile.TemporaryDirectory() as tmp:
         with tarfile.open(tar_file) as tar:
             logger.debug(f"extract to {tmp}")
-            tar.extractall(tmp)
+            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
+            
+            def safe_extract(tar, path=".", members=None, *, numeric_owner=False):
+            
+                for member in tar.getmembers():
+                    member_path = os.path.join(path, member.name)
+                    if not is_within_directory(path, member_path):
+                        raise Exception("Attempted Path Traversal in Tar File")
+            
+                tar.extractall(path, members, numeric_owner=numeric_owner) 
+                
+            
+            safe_extract(tar, tmp)
 
         strip_prefix_dir = (
             pathlib.Path(tmp).joinpath(strip_prefix + os.path.sep).resolve()