explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-10 19:57:17 +03:00
Code Issues Packages Projects Releases Wiki Activity

Check for unsafe paths in tarfile.extractall (CVE-2007-4559) (#11746)

Browse Source 
* Adding tarfile member sanitization to extractall()

* Format

* Simplify and add error message

* Fix import

* Add comment about CVE

Co-authored-by: TrellixVulnTeam <charles.mcfarland@trellix.com>
This commit is contained in:
Adriane Boyd 2022-11-07 10:43:34 +01:00 committed by GitHub
parent b76222e56a
commit e91b47a226
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 20 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
spacy/cli/project/remote_storage.py
View File

@ -10,6 +10,7 @@ from .._util import get_hash, get_checksum, download_file, ensure_pathy
from ...util import make_tempdir, get_minor_version, ENV_VARS, check_bool_env_var
from ...git_info import GIT_VERSION
from ... import about
from ...errors import Errors
if TYPE_CHECKING:
from pathy import Pathy # noqa: F401
@ -84,7 +85,23 @@ class RemoteStorage:
with tarfile.open(tar_loc, mode=mode_string) as tar_file:
# This requires that the path is added correctly, relative
# to root. This is how we set things up in push()
tar_file.extractall(self.root)
# Disallow paths outside the current directory for the tar
# file (CVE-2007-4559, directory traversal vulnerability)
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):
for member in tar.getmembers():
member_path = os.path.join(path, member.name)
if not is_within_directory(path, member_path):
raise ValueError(Errors.E852)
tar.extractall(path)
safe_extract(tar_file, self.root)
return url
def find(

2
spacy/errors.py
View File

@ -544,6 +544,8 @@ class Errors(metaclass=ErrorsWithCodes):
"during training, make sure to include it in 'annotating components'")
# New errors added in v3.x
E852 = ("The tar file pulled from the remote attempted an unsafe path "
"traversal.")
E853 = ("Unsupported component factory name '{name}'. The character '.' is "
"not permitted in factory names.")
E854 = ("Unable to set doc.ents. Check that the 'ents_filter' does not "