MLIA-961 Update pre-commit hook versions

- Update dependencies in .pre-commit.yaml
- Fix code issues with new linters

Change-Id: I36964ecf1a405dd8faac01b4470b56122a7cad17
Signed-off-by: Benjamin Klimczak <benjamin.klimczak@arm.com>

4 files changed, 58 insertions, 17 deletions

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 2de4fac..57ef192 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -1,4 +1,4 @@
-# SPDX-FileCopyrightText: Copyright 2022, Arm Limited and/or its affiliates.
+# SPDX-FileCopyrightText: Copyright 2022-2023, Arm Limited and/or its affiliates.
 # SPDX-License-Identifier: Apache-2.0
 # Pre-commit checks
 #
@@ -11,7 +11,7 @@
 
 repos:
 - repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v4.3.0
+  rev: v4.4.0
   hooks:
     - id: check-yaml
 
@@ -38,57 +38,57 @@ repos:
       args: [--whitespaces-count, '8']
 
 - repo: https://github.com/asottile/reorder_python_imports
-  rev: v3.9.0
+  rev: v3.10.0
   hooks:
     - id: reorder-python-imports
       args: ["--application-directories", ".:src"]
 
 - repo: https://github.com/asottile/pyupgrade
-  rev: v3.2.0
+  rev: v3.10.1
   hooks:
     - id: pyupgrade
       args: ["--py38-plus"]
 
 - repo: https://github.com/psf/black
-  rev: 22.10.0
+  rev: 23.7.0
   hooks:
     - id: black
 
 - repo: https://github.com/PyCQA/flake8
-  rev: '5.0.4'
+  rev: 6.1.0
   hooks:
     - id: flake8
 
 - repo: https://github.com/PyCQA/pydocstyle
-  rev: 6.1.1
+  rev: 6.3.0
   hooks:
     - id: pydocstyle
 
 - repo: https://github.com/markdownlint/markdownlint
-  rev: v0.11.0
+  rev: v0.12.0
   hooks:
     - id: markdownlint
       args: ["-r", "~MD024,~MD002"]
 
 - repo: https://github.com/ryanrhee/shellcheck-py
-  rev: v0.8.0.4
+  rev: v0.9.0.5
   hooks:
     - id: shellcheck
       args: [-f, gcc, -x]
 
 - repo: https://github.com/fsfe/reuse-tool
-  rev: v1.0.0
+  rev: v2.1.0
   hooks:
     - id: reuse
 
 - repo: https://github.com/PrincetonUniversity/blocklint
-  rev: v0.2.3
+  rev: v0.2.4
   hooks:
     - id: blocklint
       exclude: setup.cfg
 
 - repo: https://github.com/PyCQA/bandit
-  rev: '1.7.4'
+  rev: 1.7.5
   hooks:
     - id: bandit
       args: ["--skip", "B101"]
diff --git a/README.md b/README.md
index 7c9209a..725af53 100644
--- a/README.md
+++ b/README.md
@@ -64,8 +64,8 @@ typical setup for MLIA requires:
   tested on this one specifically)
 * Python® >= 3.8.1
 * Ethos™-U Vela dependencies (Linux® only)
-  * For more details, please refer to the
-    [prerequisites of Vela](https://pypi.org/project/ethos-u-vela/)
+   * For more details, please refer to the
+     [prerequisites of Vela](https://pypi.org/project/ethos-u-vela/)
 
 ## Installation
 
diff --git a/RELEASES.md b/RELEASES.md
index 992b146..4ac1b9b 100644
--- a/RELEASES.md
+++ b/RELEASES.md
@@ -135,7 +135,7 @@ scheme.
 * Ethos-U operator compatibility, performance estimation and optimization
   advice
 * Arm IP support:
-  * Ethos-U55 via Corstone-300 and Corstone-310
-  * Ethos-U65 via Corstone-300
+   * Ethos-U55 via Corstone-300 and Corstone-310
+   * Ethos-U65 via Corstone-300
 
   Note: Corstone-310 is available on AVH only.
diff --git a/src/mlia/backend/install.py b/src/mlia/backend/install.py
index 721b660..f405511 100644
--- a/src/mlia/backend/install.py
+++ b/src/mlia/backend/install.py
@@ -11,6 +11,7 @@ from abc import abstractmethod
 from dataclasses import dataclass
 from pathlib import Path
 from typing import Callable
+from typing import Iterable
 from typing import Optional
 from typing import Union
 
@@ -177,7 +178,47 @@ class BackendInstallation(Installation):
 
             with working_directory(tmpdir / "dist", create_dir=True) as dist_dir:
                 with tarfile.open(downloaded_to) as archive:
-                    archive.extractall(dist_dir)
+
+                    def get_filtered_members(
+                        members: Iterable[tarfile.TarInfo],
+                    ) -> Iterable[tarfile.TarInfo]:
+                        """
+                        Make sure we only handle safe files from the tar file.
+
+                        To avoid traversal attacks we only allow files that are
+                        - regular files, i.e. not a symlink etc.
+                        - relative paths, i.e. no absolute file paths
+                        - not including directory traversal sequences '..'
+                        """
+                        for member in members:
+                            try:
+                                if not (member.isfile() or member.isdir()):
+                                    raise ValueError("Path is not a regular file.")
+                                path = Path(member.path)
+                                if path.is_absolute():
+                                    raise ValueError(
+                                        "Path is absolute, but must be relative."
+                                    )
+                                abs_path = (dist_dir / path).resolve()
+                                abs_path.relative_to(dist_dir)
+                                yield member
+                            except ValueError as ex:
+                                logger.warning(
+                                    "File '%s' ignored while extracting from %s: %s",
+                                    member.path,
+                                    downloaded_to,
+                                    ex,
+                                )
+
+                    # Filter files from the tarfile to avoid traversal attacks.
+                    # Note: bandit is still putting out a low severity /
+                    # low confidence warning despite the check
+                    # From Python 3.8.17 on there is a built-in feature to fix
+                    # this using the new argument filter="data", see
+                    # https://docs.python.org/3.8/library/tarfile.html#tarfile.TarFile.extractall
+                    archive.extractall(  # nosec
+                        dist_dir, members=get_filtered_members(archive.getmembers())
+                    )
 
                 backend_path = dist_dir
                 if self.backend_installer: