Add bandit to pre-commit to detect common security issues

.pre-commit-config.yaml

@@ -979,6 +979,23 @@ repos:
         files: ^airflow/providers/.*/provider\.yaml|^docs/.*
         additional_dependencies: ['rich>=12.4.4', 'pyyaml', 'jinja2']
         require_serial: true
+      - id: bandit
+        name: bandit
+        description: "Bandit is a tool for finding common security issues in Python code"
+        entry: bandit
+        language: python
+        language_version: python3
+        types: [ python ]
+        additional_dependencies: ['bandit>=1.7.5']
+        require_serial: true
+        files: ^airflow/.*
+        exclude:
+          airflow/example_dags/.*
+        args:
+          - "--skip"
+          - "B301,B324,B403,B404,B603"
+          - "--severity-level"
+          - "high"  # TODO: remove this line when we fix all the issues
         ## ADD MOST PRE-COMMITS ABOVE THAT LINE
         # The below pre-commits are those requiring CI image to be built
       - id: mypy-dev

STATIC_CODE_CHECKS.rst

@@ -140,6 +140,8 @@ require Breeze Docker image to be built locally.
 +-----------------------------------------------------------+--------------------------------------------------------------+---------+
 | ID                                                        | Description                                                  | Image   |
 +===========================================================+==============================================================+=========+
+| bandit                                                    | bandit                                                       |         |
++-----------------------------------------------------------+--------------------------------------------------------------+---------+
 | blacken-docs                                              | Run black on Python code blocks in documentation files       |         |
 +-----------------------------------------------------------+--------------------------------------------------------------+---------+
 | check-aiobotocore-optional                                | Check if aiobotocore is an optional dependency only          |         |

airflow/cli/cli_config.py

@@ -771,7 +771,7 @@ def string_lower_type(val):
 )
 ARG_INTERNAL_API_HOSTNAME = Arg(
     ("-H", "--hostname"),
-    default="0.0.0.0",
+    default="0.0.0.0",  # nosec
     help="Set the hostname on which to run the web server",
 )
 ARG_INTERNAL_API_ACCESS_LOGFILE = Arg(

airflow/cli/commands/internal_api_command.py

@@ -73,7 +73,7 @@ def internal_api(args):
         log.info(f"Starting the Internal API server on port {args.port} and host {args.hostname}.")
         app = create_app(testing=conf.getboolean("core", "unit_test_mode"))
         app.run(
-            debug=True,
+            debug=True,  # nosec
             use_reloader=not app.config["TESTING"],
             port=args.port,
             host=args.hostname,

airflow/providers/cncf/kubernetes/python_kubernetes_script.py

@@ -22,6 +22,7 @@
 from collections import deque
 
 import jinja2
+from jinja2 import select_autoescape
 
 
 def _balance_parens(after_decorator):
@@ -83,6 +84,10 @@ def write_python_script(
             loader=template_loader, undefined=jinja2.StrictUndefined
         )
     else:
-        template_env = jinja2.Environment(loader=template_loader, undefined=jinja2.StrictUndefined)
+        template_env = jinja2.Environment(
+            loader=template_loader,
+            undefined=jinja2.StrictUndefined,
+            autoescape=select_autoescape(["html", "xml"]),
+        )
     template = template_env.get_template("python_kubernetes_script.jinja2")
     template.stream(**jinja_context).dump(filename)

airflow/providers/ftp/hooks/ftp.py

@@ -18,7 +18,7 @@
 from __future__ import annotations
 
 import datetime
-import ftplib
+import ftplib  # nosec: B402
 from typing import Any, Callable
 
 from airflow.hooks.base import BaseHook
@@ -58,7 +58,7 @@ def get_conn(self) -> ftplib.FTP:
         if self.conn is None:
             params = self.get_connection(self.ftp_conn_id)
             pasv = params.extra_dejson.get("passive", True)
-            self.conn = ftplib.FTP(params.host, params.login, params.password)
+            self.conn = ftplib.FTP(params.host, params.login, params.password)  # nosec: B321
             self.conn.set_pasv(pasv)
 
         return self.conn
@@ -277,7 +277,7 @@ def get_conn(self) -> ftplib.FTP:
             if params.port:
                 ftplib.FTP_TLS.port = params.port
 
-            self.conn = ftplib.FTP_TLS(params.host, params.login, params.password)
+            self.conn = ftplib.FTP_TLS(params.host, params.login, params.password)  # nosec: B321
             self.conn.set_pasv(pasv)
 
         return self.conn

airflow/providers/ftp/operators/ftp.py

@@ -20,7 +20,7 @@
 
 import os
 import socket
-from ftplib import FTP_PORT
+from ftplib import FTP_PORT  # nosec: B402
 from functools import cached_property
 from pathlib import Path
 from typing import Any, Sequence

airflow/providers/ftp/sensors/ftp.py

@@ -17,7 +17,7 @@
 # under the License.
 from __future__ import annotations
 
-import ftplib
+import ftplib  # nosec: B402
 import re
 from typing import TYPE_CHECKING, Sequence
 

airflow/utils/python_virtualenv.py

@@ -24,6 +24,7 @@
 from pathlib import Path
 
 import jinja2
+from jinja2 import select_autoescape
 
 from airflow.utils.decorators import remove_task_decorator as _remove_task_decorator
 from airflow.utils.process_utils import execute_in_subprocess
@@ -140,6 +141,10 @@ def write_python_script(
             loader=template_loader, undefined=jinja2.StrictUndefined
         )
     else:
-        template_env = jinja2.Environment(loader=template_loader, undefined=jinja2.StrictUndefined)
+        template_env = jinja2.Environment(
+            loader=template_loader,
+            undefined=jinja2.StrictUndefined,
+            autoescape=select_autoescape(["html", "xml"]),
+        )
     template = template_env.get_template("python_virtualenv_script.jinja2")
     template.stream(**jinja_context).dump(filename)

dev/breeze/src/airflow_breeze/pre_commit_ids.py

@@ -24,6 +24,7 @@
 
 PRE_COMMIT_LIST = [
     "all",
+    "bandit",
     "blacken-docs",
     "check-aiobotocore-optional",
     "check-airflow-k8s-not-used",