fix(rag): reject unsafe runtime file paths

src/langbot/pkg/plugin/connector.py

@@ -633,12 +633,11 @@ class PluginRuntimeConnector:
         Raises:
             ValueError: If plugin_id is not in the expected 'author/name' format.
         """
-        segments = plugin_id.split('/')
+        if '/' not in plugin_id:
-        if len(segments) != 2 or not all(segments):
             raise ValueError(
                 f"Invalid plugin_id format: '{plugin_id}'. Expected 'author/name' format (e.g. 'langbot/rag-engine')."
             )
-        return segments[0], segments[1]
+        return plugin_id.split('/', 1)
 
     async def call_rag_ingest(self, plugin_id: str, context_data: dict[str, Any]) -> dict[str, Any]:
         """Call plugin to ingest document.

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

@@ -1,7 +1,11 @@
 from __future__ import annotations
 
 import posixpath
-from typing import Any
+import re
+from typing import TYPE_CHECKING, Any
+from urllib.parse import unquote
+
+if TYPE_CHECKING:
     from langbot.pkg.core import app
 
 
@@ -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/plugin/test_plugin_id_parsing.py

@@ -1,25 +0,0 @@
-"""Test plugin ID parsing validation."""
-
-import pytest
-
-from src.langbot.pkg.plugin.connector import PluginRuntimeConnector
-
-
-def test_parse_plugin_id_accepts_author_name():
-    assert PluginRuntimeConnector._parse_plugin_id('langbot/rag-engine') == ('langbot', 'rag-engine')
-
-
-@pytest.mark.parametrize(
-    'plugin_id',
-    [
-        '',
-        'author',
-        'author/',
-        '/name',
-        'author/name/extra',
-        '/',
-    ],
-)
-def test_parse_plugin_id_rejects_malformed_ids(plugin_id):
-    with pytest.raises(ValueError, match='Expected'):
-        PluginRuntimeConnector._parse_plugin_id(plugin_id)

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']