Skip to content

CVE-2007-4559 Patch #72

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
TrellixVulnTeam wants to merge 2 commits into
base: main
Choose a base branch
from
Open

CVE-2007-4559 Patch #72

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a9ba41b
Adding tarfile member sanitization to extractall()
PatchTester Oct 3, 2022
ab8e065
Adding numeric_owner as keyword arguement
TrellixVulnTeam Oct 4, 2022
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
42 changes: 40 additions & 2 deletions model-training/transcribe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,26 @@ def _asr_on_tarpaths_chunk(chunk_args):
os.makedirs(tmp_dir)
try:
with tarfile.open(audio_tarpath) as audio_tarfile:
audio_tarfile.extractall(path=tmp_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(audio_tarfile, path=tmp_dir)
except OSError as exc:
# Skip long-named audio files
if exc.errno == errno.ENAMETOOLONG:
Expand All @@ -91,7 +110,26 @@ def _asr_on_tarpaths_chunk(chunk_args):
m for m in members
if len(m.name) <= os.pathconf("/", "PC_NAME_MAX")
]
audio_tarfile.extractall(path=tmp_dir, members=healthy_members)
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(audio_tarfile, path=tmp_dir, members=healthy_members)
warnings.warn(
f"Some audio files were dropped from {audio_tarpath} "
"because they have long file names"
Expand Down