Skip to content

fix: add path traversal validation to datapoints endpoints #2610

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
q1uf3ng wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: add path traversal validation to datapoints endpoints #2610

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
14 changes: 14 additions & 0 deletions lit_nlp/app.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -215,6 +215,18 @@ def _reconstitute_inputs(
)
return [index[ex] if isinstance(ex, str) else ex for ex in inputs]

def _validate_data_path(self, path: str) -> str:
"""Validate that a user-supplied path does not escape the data directory."""
resolved = os.path.realpath(path)
if self._data_dir:
base = os.path.realpath(self._data_dir)
if not resolved.startswith(base + os.sep) and resolved != base:
raise ValueError(
f'Path must be within data_dir ({self._data_dir})')
elif '..' in os.path.normpath(path).split(os.sep):
raise ValueError('Path traversal is not allowed')
return resolved

def _save_datapoints(
self,
data,
Expand All @@ -231,6 +243,7 @@ def _save_datapoints(
if self._demo_mode:
logging.warning('Attempted to save datapoints in demo mode.')
return None
path = self._validate_data_path(path)
return self._datasets[dataset_name].save(data['inputs'], path)

def _load_datapoints(
Expand All @@ -249,6 +262,7 @@ def _load_datapoints(
if self._demo_mode:
logging.warning('Attempted to load datapoints in demo mode.')
return None
path = self._validate_data_path(path)
dataset = self._datasets[dataset_name].load(path)
return dataset.indexed_examples

Expand Down