website/server/src/middleware/botScore.js

// ── Bot / scanner scoring and IP banning ──────────────────────────────────
//
// This app has no WordPress, Drupal, phpMyAdmin, .env exposure, etc. Any hit on
// those well-known scanner targets is therefore pure bot signal. Two separate
// jobs happen here, and it matters that they stay separate:
//
//   1. Junk-path 404: every hit to a known scanner path is 404'd immediately and
//      UNCONDITIONALLY — independent of any IP score or ban state. Much of the
//      scanning traffic here comes through Cloudflare edge ranges (104.23.x,
//      162.158.x, 172.68-71.x), i.e. a large rotating pool of source IPs, so we
//      must never give a fresh IP a "free pass" on a junk path while its score
//      warms up. The 404 is the primary, always-on defense.
//
//   2. Per-IP temp-ban: scoring accumulates per IP and, past a threshold, bans
//      that IP from ALL routes for a while. This exists mainly to protect the
//      real /admin login from credential stuffing once a scanner pivots from
//      probing junk to attacking login — NOT to stop the scanning itself (fresh
//      IPs are cheap for this actor, so an IP ban can't win that race). Because
//      of that we bias toward a slightly LOWER threshold rather than a high one
//      tuned to avoid false positives from a small/stable IP pool.
//
// State is a single-instance in-memory Map — fine for one Node process. Scores
// decay after a quiet period so a transient burst does not ban an IP forever.
//
// All time-based logic takes an optional `now` argument (defaulting to
// Date.now()) so the decay/ban windows are deterministic to test.

const log = require('../utils/logger')('botscore')

// Score at/above which an IP is banned from ALL routes. Deliberately on the low
// side (see job #2 above): fresh IPs are cheap for this actor, so we'd rather
// ban an attacking IP a little early than tune high to protect a stable pool.
const BAN_THRESHOLD = 80
// How long a ban lasts.
const BAN_MS = 60 * 60 * 1000 // 1 hour
// Quiet period after which a non-banned IP's accumulated score resets to 0.
const QUIET_MS = 30 * 60 * 1000 // 30 min
// Points added for a failed /admin login (wired in from the auth controller).
const LOGIN_FAIL_POINTS = 34
// Points for a tripped honeypot — an unambiguous bot, ban on sight.
const HONEYPOT_POINTS = BAN_THRESHOLD

// Weighted scanner paths, matched as a prefix against the lowercased request
// path, FIRST match wins — so more specific paths must precede their prefixes
// (e.g. /wp-admin/install.php before /wp-admin). Heavier weights = more damning.
//
// /wp-admin/install.php is by far the most-hit junk path in the real Pangolin
// access logs (from many rotating IPs), so it carries the single highest weight:
// a lone hit exceeds the ban threshold on its own — effectively a 1-hit ban —
// and outweighs every other individual path.
const PATH_WEIGHTS = [
  ['/wp-admin/install.php', 200], // top offender in prod logs — near 1-hit ban
  ['/.env', 100],
  ['/.git', 100],
  ['/.aws', 100],
  ['/wp-login.php', 100],
  ['/xmlrpc.php', 100],
  ['/wp-admin', 50],
  ['/administrator', 50],
  ['/phpmyadmin', 50],
  ['/mysql', 50],
  ['/wp-content', 40],
  ['/wp-includes', 40],
  ['/wp-json', 40],
  ['/user/login', 40], // Drupal
  ['/console', 40],
  ['/actuator', 40], // Spring Boot
  ['/vendor/phpunit', 100],
  ['/cgi-bin', 40],
]

// ip -> { score, lastSeen, bannedUntil }
const store = new Map()

// ── Recent-events ring buffer ────────────────────────────────────────────────
// A bounded, most-recent-first log of notable events (scanner hit, ban, honeypot,
// login failure) so admins can see recent activity without tailing container
// logs. In-memory only, matching the store — not persisted. Oldest entries fall
// off once EVENT_CAP is reached. Each event: { ts, ip, type, path, points,
// score, reason }.
const EVENT_CAP = 300
const events = []

function recordEvent(evt) {
  events.push(evt)
  if (events.length > EVENT_CAP) events.shift()
}

// Most-recent-first slice of the event buffer (default: whole buffer, capped).
function recentEvents(limit = EVENT_CAP) {
  const n = Math.min(limit, events.length)
  const out = new Array(n)
  for (let i = 0; i < n; i++) out[i] = events[events.length - 1 - i]
  return out
}

// Return the scanner weight for a request path (0 if it is a legitimate path).
function scoreForPath(pathname) {
  const p = String(pathname || '').toLowerCase()
  for (const [prefix, weight] of PATH_WEIGHTS) {
    if (p === prefix || p.startsWith(prefix)) return weight
  }
  return 0
}

function getEntry(ip) {
  let e = store.get(ip)
  if (!e) {
    e = { score: 0, lastSeen: 0, bannedUntil: 0 }
    store.set(ip, e)
  }
  return e
}

function isBanned(ip, now = Date.now()) {
  const e = store.get(ip)
  return Boolean(e && e.bannedUntil > now)
}

// Add points to an IP's score. Applies quiet-period decay first, then bans the
// IP if the new score crosses the threshold. Returns the updated entry.
//
// `path` is the request path when the points came from a scanned URL (else null),
// recorded into the event buffer alongside the resulting score.
function addScore(ip, points, now = Date.now(), reason = 'scan', path = null) {
  const e = getEntry(ip)
  // Decay: if the IP has been quiet longer than QUIET_MS (and is not currently
  // banned), forget its accumulated score before adding the new hit.
  if (e.bannedUntil <= now && e.lastSeen && now - e.lastSeen > QUIET_MS) {
    e.score = 0
  }
  e.score += points
  e.lastSeen = now
  const justBanned = e.score >= BAN_THRESHOLD && e.bannedUntil <= now
  if (justBanned) {
    e.bannedUntil = now + BAN_MS
    log.warn('IP banned', { ip, score: e.score, reason, banMs: BAN_MS })
  }
  // Record the scoring event, then a distinct ban event if this hit crossed the
  // threshold — so the feed shows both "why" (the hit) and the resulting ban.
  recordEvent({ ts: now, ip, type: reason, path, points, score: e.score, reason })
  if (justBanned) {
    recordEvent({ ts: now, ip, type: 'ban', path, points: 0, score: e.score, reason })
  }
  return e
}

// Points for a failed real login — called from the auth controller.
function recordLoginFailure(ip, now = Date.now()) {
  return addScore(ip, LOGIN_FAIL_POINTS, now, 'login-fail')
}

// A tripped honeypot: instant ban-worthy score.
function recordHoneypot(ip, now = Date.now()) {
  return addScore(ip, HONEYPOT_POINTS, now, 'honeypot')
}

// Early middleware: mounted before routing so banned IPs never reach a real
// handler. Everything here 404s (never 403) so we never confirm a path or a ban.
function guard(req, res, next) {
  const ip = req.ip
  const now = Date.now()

  // (1) Known junk/scanner path → 404 FIRST, unconditionally. This is evaluated
  // and returned before any ban check, so the 404 is fully independent of this
  // IP's score/ban state: a scanner cycling through fresh Cloudflare IPs gets no
  // free pass on a junk path. Scoring still runs (it accrues toward a /admin ban
  // if the IP is reused), but the 404 does not depend on it.
  const points = scoreForPath(req.path)
  if (points > 0) {
    const e = addScore(ip, points, now, 'scan', req.path)
    log.warn('scanner path hit', { ip, path: req.path, points, score: e.score })
    return notFound(res)
  }

  // (2) Non-junk path → block only if this IP is already banned (the
  // credential-stuffing guard for the real /admin login), else let it through.
  if (isBanned(ip, now)) {
    log.debug('blocked banned IP', { ip, path: req.path })
    return notFound(res)
  }

  return next()
}

// Uniform 404 — mirrors the SPA/API "Not found" shape without leaking anything.
function notFound(res) {
  return res.status(404).json({ message: 'Not found' })
}

// ── Cleanup sweep ──────────────────────────────────────────────────────────
// Every unique IP that hits a scored path adds an entry and nothing else evicts
// it, so the store would grow unbounded. Periodically drop entries that are no
// longer meaningful: NOT banned and quiet longer than QUIET_MS (their score
// would already reset to 0 on next touch anyway). Banned entries, and entries
// still inside their quiet decay window, are left untouched. Returns the count
// removed. The eviction age reuses QUIET_MS; SWEEP_INTERVAL_MS is only cadence.
const SWEEP_INTERVAL_MS = 10 * 60 * 1000 // 10 min

function sweep(now = Date.now()) {
  let removed = 0
  for (const [ip, e] of store) {
    if (e.bannedUntil <= now && now - e.lastSeen > QUIET_MS) {
      store.delete(ip)
      removed++
    }
  }
  if (removed > 0) log.debug('store sweep', { removed, remaining: store.size })
  return removed
}

let sweepTimer = null

function startSweeper() {
  if (sweepTimer) return sweepTimer
  sweepTimer = setInterval(() => sweep(), SWEEP_INTERVAL_MS)
  // Never let the sweep timer alone keep the event loop alive (tests, shutdown).
  if (sweepTimer.unref) sweepTimer.unref()
  return sweepTimer
}

function stopSweeper() {
  if (sweepTimer) {
    clearInterval(sweepTimer)
    sweepTimer = null
  }
}

// Start sweeping on load — this is a single long-lived process.
startSweeper()

// Snapshot of every IP currently in the store, for the admin view: score, ban
// state, when the ban lifts, and last-seen. Most-recently-seen first.
function listState(now = Date.now()) {
  const out = []
  for (const [ip, e] of store) {
    out.push({
      ip,
      score: e.score,
      banned: e.bannedUntil > now,
      bannedUntil: e.bannedUntil || 0,
      lastSeen: e.lastSeen || 0,
    })
  }
  out.sort((a, b) => b.lastSeen - a.lastSeen)
  return out
}

// Manually clear a single IP's entry (admin emergency unban / false positive).
// Fully removes it from the store, so it is neither banned nor carrying score.
// Returns true if an entry existed and was removed.
function unban(ip) {
  return store.delete(ip)
}

// Test/ops helpers.
function _reset() {
  store.clear()
  events.length = 0
}
function _snapshot(ip) {
  const e = store.get(ip)
  return e ? { ...e } : null
}

module.exports = {
  guard,
  scoreForPath,
  addScore,
  isBanned,
  recordLoginFailure,
  recordHoneypot,
  recentEvents,
  listState,
  unban,
  sweep,
  startSweeper,
  stopSweeper,
  _reset,
  _snapshot,
  // Exported for tests / tuning.
  BAN_THRESHOLD,
  BAN_MS,
  QUIET_MS,
  LOGIN_FAIL_POINTS,
  HONEYPOT_POINTS,
  SWEEP_INTERVAL_MS,
}