From 49c5ac07ed6d73baf171798772c8ad8ec72d4c06 Mon Sep 17 00:00:00 2001
From: "corridor-security[bot]"
 <203152403+corridor-security[bot]@users.noreply.github.com>
Date: Thu, 9 Jul 2026 06:10:27 +0000
Subject: [PATCH] Fix: Fix Regex pattern injection via user-controlled ripgrep
 search pattern

---
 .mcp.json                                           | 12 ------------
 .../langchain/agents/middleware/file_search.py      | 13 ++++++++++++-
 2 files changed, 12 insertions(+), 13 deletions(-)
 delete mode 100644 .mcp.json

diff --git a/.mcp.json b/.mcp.json
deleted file mode 100644
index c55e4cb21cc..00000000000
--- a/.mcp.json
+++ /dev/null
@@ -1,12 +0,0 @@
-{
-  "mcpServers": {
-    "docs-langchain": {
-      "type": "http",
-      "url": "https://docs.langchain.com/mcp"
-    },
-    "reference-langchain": {
-      "type": "http",
-      "url": "https://reference.langchain.com/mcp"
-    }
-  }
-}
diff --git a/libs/langchain_v1/langchain/agents/middleware/file_search.py b/libs/langchain_v1/langchain/agents/middleware/file_search.py
index 89651015718..bdb163119f7 100644
--- a/libs/langchain_v1/langchain/agents/middleware/file_search.py
+++ b/libs/langchain_v1/langchain/agents/middleware/file_search.py
@@ -21,6 +21,9 @@ from langchain_core.tools import tool
 
 from langchain.agents.middleware.types import AgentMiddleware, AgentState, ContextT, ResponseT
 
+_MAX_REGEX_PATTERN_LENGTH = 1000
+_MAX_REGEX_LINE_LENGTH = 10000
+
 
 def _is_within_root(candidate: Path, root: Path) -> bool:
     """Return True iff `candidate` resolves to a path inside `root` (symlinks resolved).
@@ -358,7 +361,13 @@ class FilesystemFileSearchMiddleware(AgentMiddleware[AgentState[ResponseT], Cont
         if not base_full.exists():
             return {}
 
-        regex = re.compile(pattern)
+        if len(pattern) > _MAX_REGEX_PATTERN_LENGTH:
+            return {}
+
+        try:
+            regex = re.compile(pattern)
+        except re.error:
+            return {}
         results: dict[str, list[tuple[int, str]]] = {}
 
         # Walk directory tree without following symlinked directories so traversal
@@ -390,6 +399,8 @@ class FilesystemFileSearchMiddleware(AgentMiddleware[AgentState[ResponseT], Cont
 
                 # Search content
                 for line_num, line in enumerate(content.splitlines(), 1):
+                    if len(line) > _MAX_REGEX_LINE_LENGTH:
+                        continue
                     if regex.search(line):
                         virtual_path = "/" + str(file_path.relative_to(self.root_path))
                         if virtual_path not in results: