From 77ad3738855e02f0dbb6c49f29101bb487643edb Mon Sep 17 00:00:00 2001
From: thethreemagi <thethreemagi@outlook.com>
Date: Tue, 1 Sep 2026 13:17:08 -0400
Subject: [PATCH] join: honeypot field + server-side validation on POST /join

Three bot submissions landed 2026-08-30 with both selects carrying the
placeholder label "Select one..." - required= is browser-only and a direct
POST skips it. Adds a hidden honeypot (answers 303 so the bot sees success)
and server-side checks on name, email, children, interested_in and source.
Rejections are logged with the client IP and never touch any store.
---
 app/app.py | 62 +++++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 57 insertions(+), 5 deletions(-)

diff --git a/app/app.py b/app/app.py
index 904e9bc..d1c02f3 100644
--- a/app/app.py
+++ b/app/app.py
@@ -1,6 +1,6 @@
-import json, os, time, datetime, urllib.request, urllib.parse
+import json, os, re, time, datetime, urllib.request, urllib.parse
 from pathlib import Path
-from fastapi import FastAPI, Form
+from fastapi import FastAPI, Form, Request
 from fastapi.responses import FileResponse, HTMLResponse, RedirectResponse
 from fastapi.staticfiles import StaticFiles
 
@@ -634,7 +634,10 @@ def thanks_body():
 </div></section>"""
 
 
-def join_body():
+def join_body(error=""):
+    err_html = (
+        '<div style="background:#FDECEC;border:1px solid #E4A0A0;color:#8A2B2B;padding:12px 14px;border-radius:10px;font-size:14.5px;margin-bottom:4px">'
+        + error + "</div>") if error else ""
     faq_html = "".join(f'<div class="faq"><div class="q">{q}</div><div class="a">{a}</div></div>' for q, a in FAQ)
     return f"""
 <section style="padding:72px 0 30px"><div class="wrap" style="display:grid;grid-template-columns:repeat(auto-fit,minmax(320px,1fr));gap:52px;align-items:start">
@@ -649,7 +652,8 @@ def join_body():
 <img src="/static/img/circle-game.jpg" alt="Scouts cheering during a pack game" style="width:100%;height:280px;object-fit:cover;border-radius:16px"></div>
 <div>
 <form class="lead" method="post" action="/join">
-<div class="ft">Interest form</div>
+<div class="ft">Interest form</div>{err_html}
+<div aria-hidden="true" style="position:absolute;left:-9999px;top:auto;width:1px;height:1px;overflow:hidden"><label>Company website</label><input name="website" type="text" tabindex="-1" autocomplete="off"></div>
 <div class="frow">
 <div><label>Parent / guardian name <span class="req">*</span></label><input name="parent_name" required></div>
 <div><label>Email <span class="req">*</span></label><input type="email" name="email" required></div>
@@ -747,10 +751,58 @@ def pipeline_notify(rec, sheet_error=None):
     except Exception:
         return False
 
+# --- form integrity --------------------------------------------------------
+# 2026-08-30: three bot submissions landed with both <select> fields carrying
+# the placeholder label "Select one...". `required` is browser-only, and a
+# direct POST skips it entirely. Validate server-side; honeypot the rest.
+VALID_INTERESTED = {
+    "Pack 73 (Cub Scouts, K-5)",
+    "Troop 73 (Scouts BSA, 11-17)",
+    "Both / kids spanning ages",
+}
+EMAIL_RE = re.compile(r"^[^@\s]+@[^@\s.]+(\.[^@\s.]+)+$")
+
+
+def lead_problem(parent_name, email, children, interested_in, source):
+    """Return a short reason string if this submission cannot be genuine."""
+    if len(parent_name.strip()) < 2:
+        return "name"
+    if not EMAIL_RE.match(email.strip()):
+        return "email"
+    if len(children.strip()) < 2:
+        return "children"
+    if interested_in.strip() not in VALID_INTERESTED:
+        return "interested_in"
+    if not source.strip():
+        return "source"
+    for v in (parent_name, children, interested_in, source):
+        if "select one" in v.lower():
+            return "placeholder"
+    return ""
+
+
 @app.post("/join")
 def join_post(parent_name: str = Form(...), email: str = Form(...), phone: str = Form(""),
               children: str = Form(""), interested_in: str = Form(""), source: str = Form(""),
-              source_place: str = Form(""), source_other: str = Form(""), message: str = Form("")):
+              source_place: str = Form(""), source_other: str = Form(""), message: str = Form(""),
+              website: str = Form(""), request: Request = None):
+    client_ip = "?"
+    if request is not None:
+        client_ip = (request.headers.get("x-forwarded-for", "").split(",")[0].strip()
+                     or (request.client.host if request.client else "?"))
+    # Honeypot. A browser never fills a field it cannot see. Answer 303 anyway
+    # so the bot books a success and has no signal to tune against.
+    if website.strip():
+        print("LEAD REJECTED (honeypot) from %s: %r <%s>"
+              % (client_ip, parent_name[:40], email[:60]), flush=True)
+        return RedirectResponse(url="/join?sent=1", status_code=303)
+    problem = lead_problem(parent_name, email, children, interested_in, source)
+    if problem:
+        print("LEAD REJECTED (%s) from %s: %r <%s>"
+              % (problem, client_ip, parent_name[:40], email[:60]), flush=True)
+        return HTMLResponse(page("Join us \u00b7 Pack & Troop 73", join_body(
+            error="We could not read that submission. Please complete every field "
+                  "marked * and send it again.")), status_code=400)
     heard_from = source.strip()
     heard_from_detail = ""
     if source == "Other school or daycare" and source_place.strip():