fix(rag): reject unsafe runtime file paths

src/langbot/pkg/api/http/service/bot.py

@@ -120,26 +120,24 @@ class BotService:
 
     async def update_bot(self, bot_uuid: str, bot_data: dict) -> None:
         """Update bot"""
-        update_data = bot_data.copy()
-
-        if 'uuid' in update_data:
-            del update_data['uuid']
+        if 'uuid' in bot_data:
+            del bot_data['uuid']
 
         # set use_pipeline_name
-        if 'use_pipeline_uuid' in update_data:
+        if 'use_pipeline_uuid' in bot_data:
             result = await self.ap.persistence_mgr.execute_async(
                 sqlalchemy.select(persistence_pipeline.LegacyPipeline).where(
-                    persistence_pipeline.LegacyPipeline.uuid == update_data['use_pipeline_uuid']
+                    persistence_pipeline.LegacyPipeline.uuid == bot_data['use_pipeline_uuid']
                 )
             )
             pipeline = result.first()
             if pipeline is not None:
-                update_data['use_pipeline_name'] = pipeline.name
+                bot_data['use_pipeline_name'] = pipeline.name
             else:
                 raise Exception('Pipeline not found')
 
         await self.ap.persistence_mgr.execute_async(
-            sqlalchemy.update(persistence_bot.Bot).values(update_data).where(persistence_bot.Bot.uuid == bot_uuid)
+            sqlalchemy.update(persistence_bot.Bot).values(bot_data).where(persistence_bot.Bot.uuid == bot_uuid)
         )
         await self.ap.platform_mgr.remove_bot(bot_uuid)
 

src/langbot/pkg/rag/service/runtime.py

@@ -1,8 +1,12 @@
 from __future__ import annotations
 
 import posixpath
-from typing import Any
-from langbot.pkg.core import app
+import re
+from typing import TYPE_CHECKING, Any
+from urllib.parse import unquote
+
+if TYPE_CHECKING:
+    from langbot.pkg.core import app
 
 
 class RAGRuntimeService:
@@ -109,8 +113,17 @@ class RAGRuntimeService:
         regardless of the underlying storage provider.
         """
         # Validate storage_path to prevent path traversal
-        normalized = posixpath.normpath(storage_path)
-        if normalized.startswith('/') or '..' in normalized.split('/'):
+        decoded_path = unquote(storage_path).replace('\\', '/')
+        decoded_segments = decoded_path.split('/')
+        normalized = posixpath.normpath(decoded_path)
+        if (
+            not storage_path
+            or '\x00' in decoded_path
+            or normalized.startswith('/')
+            or '..' in decoded_segments
+            or '..' in normalized.split('/')
+            or re.match(r'^[A-Za-z]:/', normalized)
+        ):
             raise ValueError('Invalid storage path')
         content_bytes = await self.ap.storage_mgr.storage_provider.load(normalized)
         return content_bytes if content_bytes else b''

tests/unit_tests/api/http/service/test_bot_service.py

@@ -1,62 +0,0 @@
-from types import SimpleNamespace
-from unittest.mock import AsyncMock
-
-from sqlalchemy.sql.dml import Update
-
-from langbot.pkg.api.http.service.bot import BotService
-
-
-class _FakeResult:
-    def __init__(self, value):
-        self.value = value
-
-    def first(self):
-        return self.value
-
-
-class _PersistenceManager:
-    def __init__(self):
-        self.update_values = None
-
-    async def execute_async(self, statement):
-        if isinstance(statement, Update):
-            self.update_values = {
-                key: value for key, value in statement.compile().params.items() if not key.startswith('uuid_')
-            }
-            return None
-
-        return _FakeResult(SimpleNamespace(name='Updated Pipeline'))
-
-
-async def test_update_bot_copies_input_before_filtering_and_setting_pipeline_name():
-    persistence_mgr = _PersistenceManager()
-    runtime_bot = SimpleNamespace(enable=False)
-    platform_mgr = SimpleNamespace(
-        remove_bot=AsyncMock(),
-        load_bot=AsyncMock(return_value=runtime_bot),
-    )
-    ap = SimpleNamespace(
-        persistence_mgr=persistence_mgr,
-        platform_mgr=platform_mgr,
-        sess_mgr=SimpleNamespace(session_list=[]),
-    )
-    service = BotService(ap)
-    service.get_bot = AsyncMock(return_value={'uuid': 'bot-1'})
-    payload = {
-        'uuid': 'caller-owned-uuid',
-        'name': 'Test Bot',
-        'use_pipeline_uuid': 'pipeline-1',
-    }
-
-    await service.update_bot('bot-1', payload)
-
-    assert payload == {
-        'uuid': 'caller-owned-uuid',
-        'name': 'Test Bot',
-        'use_pipeline_uuid': 'pipeline-1',
-    }
-    assert persistence_mgr.update_values == {
-        'name': 'Test Bot',
-        'use_pipeline_uuid': 'pipeline-1',
-        'use_pipeline_name': 'Updated Pipeline',
-    }

tests/unit_tests/rag/test_runtime_service.py

@@ -0,0 +1,68 @@
+from __future__ import annotations
+
+from types import SimpleNamespace
+
+import pytest
+
+from langbot.pkg.rag.service.runtime import RAGRuntimeService
+
+
+class DummyStorageProvider:
+    def __init__(self, content: bytes | None = b'data'):
+        self.content = content
+        self.loaded_paths: list[str] = []
+
+    async def load(self, path: str):
+        self.loaded_paths.append(path)
+        return self.content
+
+
+def make_service(storage_provider: DummyStorageProvider) -> RAGRuntimeService:
+    return RAGRuntimeService(SimpleNamespace(storage_mgr=SimpleNamespace(storage_provider=storage_provider)))
+
+
+@pytest.mark.asyncio
+async def test_get_file_stream_normalizes_safe_path():
+    storage_provider = DummyStorageProvider()
+    service = make_service(storage_provider)
+
+    content = await service.get_file_stream('safe/./nested/file.pdf')
+
+    assert content == b'data'
+    assert storage_provider.loaded_paths == ['safe/nested/file.pdf']
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize(
+    'storage_path',
+    [
+        '',
+        '../secret.txt',
+        '/absolute/path.txt',
+        '..\\secret.txt',
+        'nested\\..\\secret.txt',
+        '%2e%2e/secret.txt',
+        'nested/%2e%2e/secret.txt',
+        'C:\\secret.txt',
+        'safe/\x00file.txt',
+    ],
+)
+async def test_get_file_stream_rejects_unsafe_paths(storage_path: str):
+    storage_provider = DummyStorageProvider()
+    service = make_service(storage_provider)
+
+    with pytest.raises(ValueError, match='Invalid storage path'):
+        await service.get_file_stream(storage_path)
+
+    assert storage_provider.loaded_paths == []
+
+
+@pytest.mark.asyncio
+async def test_get_file_stream_returns_empty_bytes_for_missing_content():
+    storage_provider = DummyStorageProvider(content=None)
+    service = make_service(storage_provider)
+
+    content = await service.get_file_stream('safe/file.pdf')
+
+    assert content == b''
+    assert storage_provider.loaded_paths == ['safe/file.pdf']