From 68193e31c530b0896784740ec90cca8e840ba477 Mon Sep 17 00:00:00 2001
From: Chris Parsons <438676+chrisparsons83@users.noreply.github.com>
Date: Mon, 18 May 2026 11:17:18 -0700
Subject: [PATCH] Block bot probe requests before routing (#444)

Fixes #344

* Add bot probe filter middleware and Sentry noise suppression

Block common bot scanning paths (wp-admin, .env, .php, etc.) in Express
before React Router handles them, preventing spurious Sentry errors.
Also filter Sentry events for React Flight protocol probes ($1:aa:aa
multipart body pattern) and any remaining bot-path 404 noise.

https://claude.ai/code/session_01Y5Ca6oxd5zyyM89acmogf7

* Tighten bot probe regex and React Flight Sentry filter

- Remove .xml, .log, .git from bot probe blocklist to avoid false positives
  on legitimate routes (e.g. /sitemap.xml)
- Tighten React Flight error filter from broad string match to precise
  wire-format pattern (/\$\d+:[a-z]/) to avoid swallowing real errors
- Remove redundant URL check from beforeSend (ignoreErrors already covers it)
- Fix missing newline at end of instrument.server.mjs

https://claude.ai/code/session_01Y5Ca6oxd5zyyM89acmogf7

---------

Co-authored-by: Claude <noreply@anthropic.com>
---
 instrument.server.mjs | 10 +++++++++-
 server/app.ts         | 12 ++++++++++++
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/instrument.server.mjs b/instrument.server.mjs
index 9159559..486b0b6 100644
--- a/instrument.server.mjs
+++ b/instrument.server.mjs
@@ -8,5 +8,13 @@ Sentry.init({
   ignoreErrors: [
     /No route matches URL ".*\.css"/,
     /No route matches URL ".*\.js"/,
+    /No route matches URL ".*\.(php|env|xml|aspx|asp|bak|sql|ini)"/i,
+    /No route matches URL ".*\/(wp-admin|wp-login|phpmyadmin|xmlrpc)"/i,
   ],
-});
\ No newline at end of file
+  beforeSend(event) {
+    const msg = event.exception?.values?.[0]?.value ?? "";
+    // Drop React Flight protocol probe errors (e.g. $1:aa:aa in multipart body)
+    if (/\$\d+:[a-z]/.test(msg)) return null;
+    return event;
+  },
+});
diff --git a/server/app.ts b/server/app.ts
index 48a9e00..2de2ca3 100644
--- a/server/app.ts
+++ b/server/app.ts
@@ -11,6 +11,18 @@ export const app = express();
 
 app.use((_, __, next) => DatabaseContext.run(db, next));
 
+// Block common bot probe paths before React Router (and Sentry) see them
+const BOT_PROBE_RE =
+  /\.(php|env|htaccess|aspx|asp|jsp|config|bak|sql|ini|swp|DS_Store)$|^\/(wp-admin|wp-login|phpmyadmin|xmlrpc|server-status|cgi-bin|shell|cmd|console|actuator)(\/|$)/i;
+
+app.use((req, res, next) => {
+  if (BOT_PROBE_RE.test(req.path)) {
+    res.status(404).end();
+    return;
+  }
+  next();
+});
+
 app.use(
   createRequestHandler({
     build: () => import("virtual:react-router/server-build") as unknown as Promise<ServerBuild>,