From a23a2e1bbe65798c037e28b1ad531a373b2f47b9 Mon Sep 17 00:00:00 2001
From: TrellixVulnTeam <charles.mcfarland@trellix.com>
Date: Fri, 7 Oct 2022 20:27:09 +0000
Subject: [PATCH] Adding tarfile member sanitization to extractall()

---
 scripts/datasets/imagenet.py   | 42 ++++++++++++++++++++++++++++++++--
 scripts/datasets/pascal_voc.py | 42 ++++++++++++++++++++++++++++++++--
 2 files changed, 80 insertions(+), 4 deletions(-)

diff --git a/scripts/datasets/imagenet.py b/scripts/datasets/imagenet.py
index c950666..d1731b1 100644
--- a/scripts/datasets/imagenet.py
+++ b/scripts/datasets/imagenet.py
@@ -85,7 +85,26 @@ def extract_train(tar_fname, target_dir, with_rec=False, num_thread=1):
             class_dir = os.path.splitext(class_fname)[0]
             os.mkdir(class_dir)
             with tarfile.open(class_fname) as f:
-                f.extractall(class_dir)
+                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(f, class_dir)
             os.remove(class_fname)
             pbar.update(1)
         pbar.close()
@@ -96,7 +115,26 @@ def extract_val(tar_fname, target_dir, with_rec=False, num_thread=1):
     os.makedirs(target_dir)
     print('Extracting ' + tar_fname)
     with tarfile.open(tar_fname) as tar:
-        tar.extractall(target_dir)
+        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, target_dir)
     # build rec file before images are moved into subfolders
     if with_rec:
         build_rec_process(target_dir, False, num_thread)
diff --git a/scripts/datasets/pascal_voc.py b/scripts/datasets/pascal_voc.py
index 636e4a1..960b584 100644
--- a/scripts/datasets/pascal_voc.py
+++ b/scripts/datasets/pascal_voc.py
@@ -35,7 +35,26 @@ def download_voc(path, overwrite=False):
         filename = download(url, path=path, overwrite=overwrite, sha1_hash=checksum)
         # extract
         with tarfile.open(filename) as tar:
-            tar.extractall(path=path)
+            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, path=path)
 
 
 #####################################################################################
@@ -49,7 +68,26 @@ def download_aug(path, overwrite=False):
         filename = download(url, path=path, overwrite=overwrite, sha1_hash=checksum)
         # extract
         with tarfile.open(filename) as tar:
-            tar.extractall(path=path)
+            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, path=path)
             shutil.move(os.path.join(path, 'benchmark_RELEASE'),
                         os.path.join(path, 'VOCaug'))
             filenames = ['VOCaug/dataset/train.txt', 'VOCaug/dataset/val.txt']