Adding tarfile member sanitization to extractall()

Author: TrellixVulnTeam

worker/nvcaffe/python/caffe/test/test_classification.py

@@ -169,7 +169,26 @@ def unzip_archive(archive):
         if tarfile.is_tarfile(archive):
             print('Extracting tarfile ...')
             with tarfile.open(archive) as tf:
-                tf.extractall(path=tmpdir)
+                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(tf, path=tmpdir)
         elif zipfile.is_zipfile(archive):
             print('Extracting zipfile ...')
             with zipfile.ZipFile(archive) as zf:

worker/pslite_nvcaffe/python/caffe/test/test_classification.py

@@ -169,7 +169,26 @@ def unzip_archive(archive):
         if tarfile.is_tarfile(archive):
             print('Extracting tarfile ...')
             with tarfile.open(archive) as tf:
-                tf.extractall(path=tmpdir)
+                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(tf, path=tmpdir)
         elif zipfile.is_zipfile(archive):
             print('Extracting zipfile ...')
             with zipfile.ZipFile(archive) as zf: