diff --git a/download.py b/download.py index 91422ca6..6f7d41aa 100644 --- a/download.py +++ b/download.py @@ -12,7 +12,26 @@ url = "https://physionet.org/files/challenge-2012/1.0.0/set-a.tar.gz?download" wget.download(url, out="data") with tarfile.open("data/set-a.tar.gz", "r:gz") as t: - t.extractall(path="data/physio") + 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(t, path="data/physio") elif sys.argv[1] == "pm25": url = "https://www.microsoft.com/en-us/research/wp-content/uploads/2016/06/STMVL-Release.zip"