MAINT Add pre-commit hook to sanitize user paths in notebook outputs

.pre-commit-config.yaml

@@ -13,6 +13,11 @@ repos:
       entry: python ./build_scripts/remove_notebook_headers.py
       language: python
       files: ^doc.*\.(ipynb)$
+    - id: sanitize-notebook-paths
+      name: Sanitize Notebook Paths
+      entry: python ./build_scripts/sanitize_notebook_paths.py
+      language: python
+      files: ^doc.*\.(ipynb)$
 
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v5.0.0

build_scripts/sanitize_notebook_paths.py

@@ -0,0 +1,129 @@
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT license.
+
+import json
+import re
+import sys
+from re import Match
+
+# Windows path: captures user prefix AND remaining path for normalization
+_WINDOWS_PATH_PATTERN = re.compile(
+    r"[A-Za-z]:\\+Users\\+[^\\]+\\+((?:[^\\\s\"',:;]+\\+)*[^\\\s\"',:;]*)",
+    re.IGNORECASE,
+)
+# Unix paths: just match the prefix
+_UNIX_PATH_PATTERNS = [
+    re.compile(r"/Users/[^/]+/"),  # macOS
+    re.compile(r"/home/[^/]+/"),  # Linux
+]
+
+
+def _windows_path_replacer(match: Match[str]) -> str:
+    """Replace Windows user path prefix with ./ and normalize backslashes to forward slashes."""
+    remainder = match.group(1)
+    normalized = remainder.replace("\\", "/")
+    # Collapse multiple forward slashes from double-backslash paths
+    return "./" + re.sub(r"/+", "/", normalized)
+
+
+def sanitize_notebook_paths(file_path: str) -> bool:
+    """
+    Remove user-specific path prefixes from notebook cell outputs.
+
+    Replaces paths like C:\\Users\\username\\project\\file.py with ./project/file.py.
+
+    Args:
+        file_path (str): Path to the .ipynb file.
+
+    Returns:
+        bool: True if the file was modified.
+    """
+    if not file_path.endswith(".ipynb"):
+        return False
+
+    with open(file_path, encoding="utf-8") as f:
+        content = json.load(f)
+
+    modified = False
+
+    for cell in content.get("cells", []):
+        for output in cell.get("outputs", []):
+            modified = _sanitize_output_field(output, "text") or modified
+            modified = _sanitize_output_field(output, "traceback") or modified
+            modified = _sanitize_output_field(output, "evalue") or modified
+            if "data" in output:
+                for mime_type in output["data"]:
+                    if mime_type.startswith("text/"):
+                        modified = _sanitize_output_field(output["data"], mime_type) or modified
+
+    if not modified:
+        return False
+
+    with open(file_path, "w", encoding="utf-8") as f:
+        json.dump(content, f, indent=1, ensure_ascii=False)
+        f.write("\n")
+
+    return True
+
+
+def _sanitize_output_field(obj: dict, key: str) -> bool:
+    """
+    Sanitize a single output field by replacing user path prefixes with ./ normalized paths.
+
+    Args:
+        obj (dict): The dict containing the field.
+        key (str): The key to sanitize.
+
+    Returns:
+        bool: True if the field was modified.
+    """
+    value = obj.get(key)
+    if value is None:
+        return False
+
+    modified = False
+
+    if isinstance(value, list):
+        new_list = []
+        for line in value:
+            if isinstance(line, str):
+                sanitized = _strip_user_paths(line)
+                if sanitized != line:
+                    modified = True
+                new_list.append(sanitized)
+            else:
+                new_list.append(line)
+        obj[key] = new_list
+    elif isinstance(value, str):
+        sanitized = _strip_user_paths(value)
+        if sanitized != value:
+            modified = True
+        obj[key] = sanitized
+
+    return modified
+
+
+def _strip_user_paths(text: str) -> str:
+    """
+    Replace user-specific path prefixes with ./ and normalize separators.
+
+    Windows paths are normalized to forward slashes. For example,
+    C:\\Users\\alice\\project\\file.py becomes ./project/file.py.
+
+    Args:
+        text (str): The text to sanitize.
+
+    Returns:
+        str: The sanitized text.
+    """
+    text = _WINDOWS_PATH_PATTERN.sub(_windows_path_replacer, text)
+    for pattern in _UNIX_PATH_PATTERNS:
+        text = pattern.sub("./", text)
+    return text
+
+
+if __name__ == "__main__":
+    modified_files = [file_path for file_path in sys.argv[1:] if sanitize_notebook_paths(file_path)]
+    if modified_files:
+        print("Sanitized user paths in:", modified_files)
+        sys.exit(1)

doc/code/auxiliary_attacks/1_gcg_azure_ml.ipynb

@@ -105,7 +105,7 @@
     {
      "data": {
       "text/plain": [
-       "Environment({'arm_type': 'environment_version', 'latest_version': None, 'image': None, 'intellectual_property': None, 'is_anonymous': False, 'auto_increment_version': False, 'auto_delete_setting': None, 'name': 'pyrit', 'description': 'PyRIT environment created from a Docker context.', 'tags': {}, 'properties': {'azureml.labels': 'latest'}, 'print_as_yaml': False, 'id': '/subscriptions/db1ba766-2ca3-42c6-a19a-0f0d43134a8c/resourceGroups/romanlutz/providers/Microsoft.MachineLearningServices/workspaces/romanlutz/environments/pyrit/versions/5', 'Resource__source_path': '', 'base_path': 'c:\\\\Users\\\\Roman\\\\git\\\\PyRIT\\\\doc\\\\code\\\\auxiliary_attacks', 'creation_context': <azure.ai.ml.entities._system_data.SystemData object at 0x0000024025678AD0>, 'serialize': <msrest.serialization.Serializer object at 0x0000024025671470>, 'version': '5', 'conda_file': None, 'build': <azure.ai.ml.entities._assets.environment.BuildContext object at 0x00000240256FC410>, 'inference_config': None, 'os_type': 'Linux', 'conda_file_path': None, 'path': None, 'datastore': None, 'upload_hash': None, 'translated_conda_file': None})"
+       "Environment({'arm_type': 'environment_version', 'latest_version': None, 'image': None, 'intellectual_property': None, 'is_anonymous': False, 'auto_increment_version': False, 'auto_delete_setting': None, 'name': 'pyrit', 'description': 'PyRIT environment created from a Docker context.', 'tags': {}, 'properties': {'azureml.labels': 'latest'}, 'print_as_yaml': False, 'id': '/subscriptions/db1ba766-2ca3-42c6-a19a-0f0d43134a8c/resourceGroups/romanlutz/providers/Microsoft.MachineLearningServices/workspaces/romanlutz/environments/pyrit/versions/5', 'Resource__source_path': '', 'base_path': './git/PyRIT/doc/code/auxiliary_attacks', 'creation_context': <azure.ai.ml.entities._system_data.SystemData object at 0x0000024025678AD0>, 'serialize': <msrest.serialization.Serializer object at 0x0000024025671470>, 'version': '5', 'conda_file': None, 'build': <azure.ai.ml.entities._assets.environment.BuildContext object at 0x00000240256FC410>, 'inference_config': None, 'os_type': 'Linux', 'conda_file_path': None, 'path': None, 'datastore': None, 'upload_hash': None, 'translated_conda_file': None})"
       ]
      },
      "execution_count": null,
@@ -199,7 +199,7 @@
       "Class BaseIntellectualPropertySchema: This is an experimental class, and may change at any time. Please see https://aka.ms/azuremlexperimental for more information.\n",
       "Your file exceeds 100 MB. If you experience low speeds, latency, or broken connections, we recommend using the AzCopyv10 tool for this file transfer.\n",
       "\n",
-      "Example: azcopy copy 'C:\\Users\\Roman\\git\\PyRIT' 'https://romanlutz0437468309.blob.core.windows.net/3f52e8b9-0bac-4c48-9e4a-a92e85a582c4-10s61nn9uso4b2p89xjypawyc7/PyRIT' \n",
+      "Example: azcopy copy './git/PyRIT' 'https://romanlutz0437468309.blob.core.windows.net/3f52e8b9-0bac-4c48-9e4a-a92e85a582c4-10s61nn9uso4b2p89xjypawyc7/PyRIT' \n",
       "\n",
       "See https://learn.microsoft.com/azure/storage/common/storage-use-azcopy-v10 for more information.\n",
       "\u001b[32mUploading PyRIT (194.65 MBs): 100%|##########| 194652493/194652493 [01:19<00:00, 2447407.71it/s] \n",

doc/code/converters/3_image_converters.ipynb

@@ -40,9 +40,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Found default environment files: ['C:\\\\Users\\\\rlundeen\\\\.pyrit\\\\.env', 'C:\\\\Users\\\\rlundeen\\\\.pyrit\\\\.env.local']\n",
-      "Loaded environment file: C:\\Users\\rlundeen\\.pyrit\\.env\n",
-      "Loaded environment file: C:\\Users\\rlundeen\\.pyrit\\.env.local\n",
+      "Found default environment files: ['./.pyrit/.env', './.pyrit/.env.local']\n",
+      "Loaded environment file: ./.pyrit/.env\n",
+      "Loaded environment file: ./.pyrit/.env.local\n",
       "QR code saved to: C:\\git\\PyRIT\\dbdata\\prompt-memory-entries\\images\\1767215000773182.png\n"
      ]
     },

doc/code/converters/4_video_converters.ipynb

@@ -40,9 +40,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Found default environment files: ['/home/vscode/.pyrit/.env', '/home/vscode/.pyrit/.env.local']\n",
-      "Loaded environment file: /home/vscode/.pyrit/.env\n",
-      "Loaded environment file: /home/vscode/.pyrit/.env.local\n"
+      "Found default environment files: ['./.pyrit/.env', './.pyrit/.env.local']\n",
+      "Loaded environment file: ./.pyrit/.env\n",
+      "Loaded environment file: ./.pyrit/.env.local\n"
      ]
     },
     {

doc/code/converters/5_file_converters.ipynb

@@ -51,10 +51,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Found default environment files: ['C:\\\\Users\\\\romanlutz\\\\.pyrit\\\\.env', 'C:\\\\Users\\\\romanlutz\\\\.pyrit\\\\.env.local']\n",
-      "Loaded environment file: C:\\Users\\romanlutz\\.pyrit\\.env\n",
-      "Loaded environment file: C:\\Users\\romanlutz\\.pyrit\\.env.local\n",
-      "TextTarget: user: C:\\Users\\romanlutz\\git\\PyRIT3\\dbdata\\prompt-memory-entries\\binaries\\1771544413320034.pdf\n"
+      "Found default environment files: ['./.pyrit/.env', './.pyrit/.env.local']\n",
+      "Loaded environment file: ./.pyrit/.env\n",
+      "Loaded environment file: ./.pyrit/.env.local\n",
+      "TextTarget: user: ./git/PyRIT3/dbdata/prompt-memory-entries/binaries/1771544413320034.pdf\n"
      ]
     },
     {
@@ -78,7 +78,7 @@
       "\u001b[37m      coffee', 'applicant_name': 'John Smith'}\u001b[0m\n",
       "\n",
       "\u001b[36m   Converted:\u001b[0m\n",
-      "\u001b[37m  C:\\Users\\romanlutz\\git\\PyRIT3\\dbdata\\prompt-memory-entries\\binaries\\1771544413320034.pdf\u001b[0m\n",
+      "\u001b[37m  ./git/PyRIT3/dbdata/prompt-memory-entries/binaries/1771544413320034.pdf\u001b[0m\n",
       "\n",
       "\u001b[34m────────────────────────────────────────────────────────────────────────────────────────────────────\u001b[0m\n"
      ]
@@ -170,7 +170,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "TextTarget: user: C:\\Users\\romanlutz\\git\\PyRIT3\\dbdata\\prompt-memory-entries\\binaries\\1771544413393574.pdf\n"
+      "TextTarget: user: ./git/PyRIT3/dbdata/prompt-memory-entries/binaries/1771544413393574.pdf\n"
      ]
     },
     {
@@ -192,7 +192,7 @@
       "\u001b[37m  This is a simple test string for PDF generation. No templates here!\u001b[0m\n",
       "\n",
       "\u001b[36m   Converted:\u001b[0m\n",
-      "\u001b[37m  C:\\Users\\romanlutz\\git\\PyRIT3\\dbdata\\prompt-memory-entries\\binaries\\1771544413393574.pdf\u001b[0m\n",
+      "\u001b[37m  ./git/PyRIT3/dbdata/prompt-memory-entries/binaries/1771544413393574.pdf\u001b[0m\n",
       "\n",
       "\u001b[34m────────────────────────────────────────────────────────────────────────────────────────────────────\u001b[0m\n"
      ]
@@ -270,7 +270,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "TextTarget: user: C:\\Users\\romanlutz\\git\\PyRIT3\\dbdata\\prompt-memory-entries\\binaries\\1771544413696795.pdf\n"
+      "TextTarget: user: ./git/PyRIT3/dbdata/prompt-memory-entries/binaries/1771544413696795.pdf\n"
      ]
     },
     {
@@ -292,7 +292,7 @@
       "\u001b[37m  Modify existing PDF\u001b[0m\n",
       "\n",
       "\u001b[36m   Converted:\u001b[0m\n",
-      "\u001b[37m  C:\\Users\\romanlutz\\git\\PyRIT3\\dbdata\\prompt-memory-entries\\binaries\\1771544413696795.pdf\u001b[0m\n",
+      "\u001b[37m  ./git/PyRIT3/dbdata/prompt-memory-entries/binaries/1771544413696795.pdf\u001b[0m\n",
       "\n",
       "\u001b[34m────────────────────────────────────────────────────────────────────────────────────────────────────\u001b[0m\n"
      ]
@@ -400,7 +400,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "TextTarget: user: C:\\Users\\romanlutz\\git\\PyRIT3\\dbdata\\prompt-memory-entries\\binaries\\1771544413782754.docx\n"
+      "TextTarget: user: ./git/PyRIT3/dbdata/prompt-memory-entries/binaries/1771544413782754.docx\n"
      ]
     },
     {
@@ -422,7 +422,7 @@
       "\u001b[37m  This is a simple test string for Word document generation.\u001b[0m\n",
       "\n",
       "\u001b[36m   Converted:\u001b[0m\n",
-      "\u001b[37m  C:\\Users\\romanlutz\\git\\PyRIT3\\dbdata\\prompt-memory-entries\\binaries\\1771544413782754.docx\u001b[0m\n",
+      "\u001b[37m  ./git/PyRIT3/dbdata/prompt-memory-entries/binaries/1771544413782754.docx\u001b[0m\n",
       "\n",
       "\u001b[34m────────────────────────────────────────────────────────────────────────────────────────────────────\u001b[0m\n"
      ]
@@ -466,7 +466,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "TextTarget: user: C:\\Users\\romanlutz\\git\\PyRIT3\\dbdata\\prompt-memory-entries\\binaries\\1771544413886346.docx\n"
+      "TextTarget: user: ./git/PyRIT3/dbdata/prompt-memory-entries/binaries/1771544413886346.docx\n"
      ]
     },
     {
@@ -488,7 +488,7 @@
       "\u001b[37m  AI Red Team Engineer\u001b[0m\n",
       "\n",
       "\u001b[36m   Converted:\u001b[0m\n",
-      "\u001b[37m  C:\\Users\\romanlutz\\git\\PyRIT3\\dbdata\\prompt-memory-entries\\binaries\\1771544413886346.docx\u001b[0m\n",
+      "\u001b[37m  ./git/PyRIT3/dbdata/prompt-memory-entries/binaries/1771544413886346.docx\u001b[0m\n",
       "\n",
       "\u001b[34m────────────────────────────────────────────────────────────────────────────────────────────────────\u001b[0m\n"
      ]

doc/code/converters/6_selectively_converting.ipynb

@@ -27,9 +27,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Found default environment files: ['/home/vscode/.pyrit/.env', '/home/vscode/.pyrit/.env.local']\n",
-      "Loaded environment file: /home/vscode/.pyrit/.env\n",
-      "Loaded environment file: /home/vscode/.pyrit/.env.local\n"
+      "Found default environment files: ['./.pyrit/.env', './.pyrit/.env.local']\n",
+      "Loaded environment file: ./.pyrit/.env\n",
+      "Loaded environment file: ./.pyrit/.env.local\n"
      ]
     }
    ],

doc/code/datasets/1_loading_datasets.ipynb

@@ -187,9 +187,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Found default environment files: ['C:\\\\Users\\\\romanlutz\\\\.pyrit\\\\.env', 'C:\\\\Users\\\\romanlutz\\\\.pyrit\\\\.env.local']\n",
-      "Loaded environment file: C:\\Users\\romanlutz\\.pyrit\\.env\n",
-      "Loaded environment file: C:\\Users\\romanlutz\\.pyrit\\.env.local\n"
+      "Found default environment files: ['./.pyrit/.env', './.pyrit/.env.local']\n",
+      "Loaded environment file: ./.pyrit/.env\n",
+      "Loaded environment file: ./.pyrit/.env.local\n"
      ]
     },
     {

doc/code/datasets/2_seed_programming.ipynb

@@ -32,9 +32,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Found default environment files: ['C:\\\\Users\\\\rlundeen\\\\.pyrit\\\\.env', 'C:\\\\Users\\\\rlundeen\\\\.pyrit\\\\.env.local']\n",
-      "Loaded environment file: C:\\Users\\rlundeen\\.pyrit\\.env\n",
-      "Loaded environment file: C:\\Users\\rlundeen\\.pyrit\\.env.local\n",
+      "Found default environment files: ['./.pyrit/.env', './.pyrit/.env.local']\n",
+      "Loaded environment file: ./.pyrit/.env\n",
+      "Loaded environment file: ./.pyrit/.env.local\n",
       "Attack Parameters: AttackParameters:\n",
       "  objective: Get the model to describe pyrit architecture based on the image\n",
       "  next_message: (2 piece(s)) Describe the image in the image_path\n",

doc/code/executor/attack/1_prompt_sending_attack.ipynb

@@ -32,9 +32,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Found default environment files: ['C:\\\\Users\\\\rlundeen\\\\.pyrit\\\\.env', 'C:\\\\Users\\\\rlundeen\\\\.pyrit\\\\.env.local']\n",
-      "Loaded environment file: C:\\Users\\rlundeen\\.pyrit\\.env\n",
-      "Loaded environment file: C:\\Users\\rlundeen\\.pyrit\\.env.local\n"
+      "Found default environment files: ['./.pyrit/.env', './.pyrit/.env.local']\n",
+      "Loaded environment file: ./.pyrit/.env\n",
+      "Loaded environment file: ./.pyrit/.env.local\n"
      ]
     },
     {
@@ -1066,9 +1066,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Found default environment files: ['C:\\\\Users\\\\rlundeen\\\\.pyrit\\\\.env', 'C:\\\\Users\\\\rlundeen\\\\.pyrit\\\\.env.local']\n",
-      "Loaded environment file: C:\\Users\\rlundeen\\.pyrit\\.env\n",
-      "Loaded environment file: C:\\Users\\rlundeen\\.pyrit\\.env.local\n"
+      "Found default environment files: ['./.pyrit/.env', './.pyrit/.env.local']\n",
+      "Loaded environment file: ./.pyrit/.env\n",
+      "Loaded environment file: ./.pyrit/.env.local\n"
      ]
     },
     {