fix(rag): reject unsafe runtime file paths

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

@@ -52,9 +52,6 @@ class ApiKeyService:
 
     async def verify_api_key(self, key: str) -> bool:
         """Verify if an API key is valid"""
-        if not isinstance(key, str) or not key.startswith('lbk_'):
-            return False
-
         result = await self.ap.persistence_mgr.execute_async(
             sqlalchemy.select(apikey.ApiKey).where(apikey.ApiKey.key == key)
         )

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

@@ -1,8 +1,12 @@
 from __future__ import annotations
 
 import posixpath
-from typing import Any
+import re
-from langbot.pkg.core import app
+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)
+        decoded_path = unquote(storage_path).replace('\\', '/')
-        if normalized.startswith('/') or '..' in normalized.split('/'):
+        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/test_apikey_service.py

@@ -1,40 +0,0 @@
-from __future__ import annotations
-
-from types import SimpleNamespace
-from unittest.mock import AsyncMock, Mock
-
-import pytest
-
-from langbot.pkg.api.http.service.apikey import ApiKeyService
-
-
-@pytest.mark.asyncio
-@pytest.mark.parametrize('api_key', [None, 123, b'lbk_bytes', '', 'plain_key', ' LBK_bad', 'sk-lbk_fake'])
-async def test_verify_api_key_rejects_non_lbk_keys_without_db_query(api_key):
-    persistence_mgr = SimpleNamespace(execute_async=AsyncMock())
-    service = ApiKeyService(SimpleNamespace(persistence_mgr=persistence_mgr))
-
-    result = await service.verify_api_key(api_key)
-
-    assert result is False
-    persistence_mgr.execute_async.assert_not_awaited()
-
-
-@pytest.mark.asyncio
-@pytest.mark.parametrize(
-    ('db_row', 'expected'),
-    [
-        (object(), True),
-        (None, False),
-    ],
-)
-async def test_verify_api_key_keeps_db_validation_for_lbk_keys(db_row, expected):
-    query_result = Mock()
-    query_result.first.return_value = db_row
-    persistence_mgr = SimpleNamespace(execute_async=AsyncMock(return_value=query_result))
-    service = ApiKeyService(SimpleNamespace(persistence_mgr=persistence_mgr))
-
-    result = await service.verify_api_key('lbk_valid_format')
-
-    assert result is expected
-    persistence_mgr.execute_async.assert_awaited_once()

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']