Skip to content

Python tool for converting files and office documents to Markdown.

Safeguard against path traversal for ZipConverter

Joel Esler6e4caac70d63
diff --git a/.gitignore b/.gitignore
index 82f92755..b6139eb7 100644
--- a/.gitignore
+++ b/.gitignore
@@ -160,3 +160,5 @@ cython_debug/
# and can be added to the global gitignore or merged into this file. For a more nuclear
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
#.idea/
+src/.DS_Store
+.DS_Store
diff --git a/src/markitdown/_markitdown.py b/src/markitdown/_markitdown.py
index 2e7e5ffd..28770f40 100644
--- a/src/markitdown/_markitdown.py
+++ b/src/markitdown/_markitdown.py
@@ -1133,27 +1133,28 @@ class ZipConverter(DocumentConverter):
extracted_zip_folder_name = (
f"extracted_{os.path.basename(local_path).replace('.zip', '_zip')}"
)
- new_folder = os.path.normpath(
+ extraction_dir = os.path.normpath(
os.path.join(os.path.dirname(local_path), extracted_zip_folder_name)
)
md_content = f"Content from the zip file `{os.path.basename(local_path)}`:\n\n"
- # Safety check for path traversal
- if not new_folder.startswith(os.path.dirname(local_path)):
- return DocumentConverterResult(
- title=None, text_content=f"[ERROR] Invalid zip file path: {local_path}"
- )
-
try:
- # Extract the zip file
+ # Extract the zip file safely
with zipfile.ZipFile(local_path, "r") as zipObj:
- zipObj.extractall(path=new_folder)
+ # Safeguard against path traversal
+ for member in zipObj.namelist():
+ member_path = os.path.normpath(os.path.join(extraction_dir, member))
+ if not os.path.commonprefix([extraction_dir, member_path]) == extraction_dir:
+ raise ValueError(f"Path traversal detected in zip file: {member}")
+
+ # Extract all files safely
+ zipObj.extractall(path=extraction_dir)
# Process each extracted file
- for root, dirs, files in os.walk(new_folder):
+ for root, dirs, files in os.walk(extraction_dir):
for name in files:
file_path = os.path.join(root, name)
- relative_path = os.path.relpath(file_path, new_folder)
+ relative_path = os.path.relpath(file_path, extraction_dir)
# Get file extension
_, file_extension = os.path.splitext(name)
@@ -1177,7 +1178,7 @@ class ZipConverter(DocumentConverter):
# Clean up extracted files if specified
if kwargs.get("cleanup_extracted", True):
- shutil.rmtree(new_folder)
+ shutil.rmtree(extraction_dir)
return DocumentConverterResult(title=None, text_content=md_content.strip())
@@ -1186,6 +1187,11 @@ class ZipConverter(DocumentConverter):
title=None,
text_content=f"[ERROR] Invalid or corrupted zip file: {local_path}",
)
+ except ValueError as ve:
+ return DocumentConverterResult(
+ title=None,
+ text_content=f"[ERROR] Security error in zip file {local_path}: {str(ve)}",
+ )
except Exception as e:
return DocumentConverterResult(
title=None,