Skip to content

Update docker-image-extract.py #3457

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
RuslanSemchenko wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Update docker-image-extract.py #3457

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
960aab1
Update docker-image-extract.py
RuslanSemchenko Mar 16, 2026
ff0e57c
Update docker-image-extract.py
RuslanSemchenko Mar 16, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
85 changes: 64 additions & 21 deletions platform/sqlite/docker-image-extract.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,25 +8,68 @@
import os
import sys

image_path = sys.argv[1]
extracted_path = sys.argv[2]

image = tarfile.open(image_path)
manifest = json.loads(image.extractfile('manifest.json').read())

for layer in manifest[0]['Layers']:
print('Found layer: %s' % layer)
layer_tar = tarfile.open(fileobj=image.extractfile(layer))

for tarinfo in layer_tar:
print(' ... %s' % tarinfo.name)
if tarinfo.isdev():
print(' --> skip device files')
def is_safe_path(basedir, path):
base = os.path.realpath(basedir)
target = os.path.realpath(path)
return os.path.commonpath([base]) == os.path.commonpath([base, target])
def is_safe_link(basedir, tarinfo):
if not (tarinfo.issym() or tarinfo.islnk()):
return True
if os.path.isabs(tarinfo.linkname):
return False
link_dir = os.path.dirname(os.path.join(basedir, tarinfo.name))
target_path = os.path.normpath(os.path.join(link_dir, tarinfo.linkname))
return is_safe_path(basedir, target_path)
def main():
if len(sys.argv) < 3:
print("Usage: python docker-image-extract.py <image.tar> <destination_dir>")
sys.exit(1)
image_path = sys.argv[1]
extracted_path = sys.argv[2]
if not os.path.exists(extracted_path):
os.makedirs(extracted_path)
extracted_path = os.path.realpath(extracted_path)
try:
image = tarfile.open(image_path)
except Exception as e:
print(f"Error opening image: {e}")
sys.exit(1)
try:
manifest_data = image.extractfile('manifest.json')
if not manifest_data:
print("Error: manifest.json not found in the image archive.")
sys.exit(1)
manifest = json.loads(manifest_data.read())
except Exception as e:
print(f"Error reading manifest: {e}")
sys.exit(1)
for layer in manifest[0]['Layers']:
print(f"Found layer: {layer}")
layer_fileobj = image.extractfile(layer)
if not layer_fileobj:
continue

dest = os.path.join(extracted_path, tarinfo.name)
if not tarinfo.isdir() and os.path.exists(dest):
print(' --> remove old version of file')
os.unlink(dest)

layer_tar.extract(tarinfo, path=extracted_path)
layer_tar = tarfile.open(fileobj=layer_fileobj)
for tarinfo in layer_tar:
dest = os.path.normpath(os.path.join(extracted_path, tarinfo.name))
if not is_safe_path(extracted_path, dest):
print(f" [!] SECURITY WARNING: Skipping unsafe path: {tarinfo.name}")
continue
if not is_safe_link(extracted_path, tarinfo):
print(f" [!] SECURITY WARNING: Skipping unsafe link: {tarinfo.name} -> {tarinfo.linkname}")
continue
Copy link
Copy Markdown

@cursor cursor Bot Mar 16, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Link targets are never validated by security check

High Severity

The is_safe_path check only validates tarinfo.name (the entry's filesystem destination) but never inspects tarinfo.linkname (the target of symlink or hardlink entries). A malicious tar can include a hardlink with a safe-looking name but a linkname like ../../etc/shadow, causing tarfile.extract to create a hard link to a sensitive file outside the extraction directory. Similarly, a symlink entry can have linkname pointing to an arbitrary absolute path. This is a separate bypass from the abspath-vs-realpath issue and matches the pattern described in CVE-2025-4138.

Fix in Cursor Fix in Web

print(f" ... {tarinfo.name}")
if tarinfo.isdev():
print(" --> skip device files")
continue
if not tarinfo.isdir() and os.path.exists(dest):
if os.path.isfile(dest) or os.path.islink(dest):
print(" --> remove old version of file")
os.unlink(dest)
try:
layer_tar.extract(tarinfo, path=extracted_path)
except Exception as e:
print(f" [!] Error extracting {tarinfo.name}: {e}")
image.close()
print("\nExtraction complete.")
if __name__ == "__main__":
main()