WordPress OSINT Inspector | Operating systems, scripting, PowerShell and security

Python, Web

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
WordPress OSINT Inspector
Auditoría pasiva de tecnologías WordPress mediante peticiones HTTP GET.
No realiza autenticación, POST, explotación ni modificación del servidor.
"""

import json
import re
import threading
import queue
import time
from datetime import datetime
from urllib.parse import urljoin, urlparse, parse_qs
from html.parser import HTMLParser
import tkinter as tk
from tkinter import ttk, messagebox, filedialog

try:
    import requests
except ImportError:
    raise SystemExit("Falta requests. Instala las dependencias con: python3 -m pip install -r requirements.txt")


APP_TITLE = "WordPress OSINT Inspector"
USER_AGENT = "WordPressOSINTInspector/1.0 (+passive security assessment)"
TIMEOUT = 12

KNOWN_PLUGINS = {
    "wp-rocket": "WP Rocket",
    "wordfence": "Wordfence",
    "wordfence-login-security": "Wordfence Login Security",
    "sg-security": "SiteGround Security",
    "wordpress-seo": "Yoast SEO",
    "wpforms": "WPForms",
    "generateblocks": "GenerateBlocks",
    "generateblocks-pro": "GenerateBlocks Pro",
    "generatepress-pro": "GeneratePress Premium",
    "advanced-database-cleaner": "Advanced Database Cleaner",
    "all-in-one-wp-security": "All In One WP Security",
    "really-simple-ssl": "Really Simple Security",
    "elementor": "Elementor",
    "contact-form-7": "Contact Form 7",
    "woocommerce": "WooCommerce",
    "akismet": "Akismet",
    "jetpack": "Jetpack",
    "updraftplus": "UpdraftPlus",
    "ithemes-security": "Solid Security",
}

KNOWN_THEMES = {
    "generatepress": "GeneratePress",
    "astra": "Astra",
    "hello-elementor": "Hello Elementor",
    "oceanwp": "OceanWP",
    "kadence": "Kadence",
    "blocksy": "Blocksy",
    "divi": "Divi",
    "flatsome": "Flatsome",
    "avada": "Avada",
}


class AssetParser(HTMLParser):
    def __init__(self):
        super().__init__()
        self.assets = []
        self.generators = []
        self.links = []

    def handle_starttag(self, tag, attrs):
        a = dict(attrs)
        if tag.lower() == "meta" and a.get("name", "").lower() == "generator":
            if a.get("content"):
                self.generators.append(a["content"])
        for key in ("src", "href"):
            value = a.get(key)
            if value and any(x in value.lower() for x in (
                "wp-content", "wp-includes", "wp-admin"
            )):
                self.assets.append(value)
        if tag.lower() == "link" and a.get("rel", "").lower() in ("https://api.w.org/", "api.w.org/"):
            if a.get("href"):
                self.links.append(a["href"])


def normalize_domain(value):
    value = value.strip()
    if not value:
        raise ValueError("Introduce un dominio.")
    if not re.match(r"^https?://", value, re.I):
        value = "https://" + value
    parsed = urlparse(value)
    if not parsed.hostname:
        raise ValueError("Dominio no válido.")
    if parsed.scheme not in ("http", "https"):
        raise ValueError("Solo se admiten HTTP y HTTPS.")
    return f"{parsed.scheme}://{parsed.netloc}"


def safe_get(session, url):
    try:
        response = session.get(url, timeout=TIMEOUT, allow_redirects=True)
        return response
    except requests.RequestException as exc:
        return {"error": str(exc)}


def version_from_text(text):
    patterns = [
        r"(?im)^\s*Version\s+([0-9]+(?:\.[0-9]+){1,3})",
        r"(?i)wordpress\s+([0-9]+(?:\.[0-9]+){1,3})",
    ]
    for pattern in patterns:
        match = re.search(pattern, text or "")
        if match:
            return match.group(1)
    return None


def unique_append(items, value):
    if value and value not in items:
        items.append(value)


def inspect_domain(domain, log_callback=None):
    base_url = normalize_domain(domain)
    session = requests.Session()
    session.headers.update({"User-Agent": USER_AGENT, "Accept": "*/*"})
    result = {
        "target": base_url,
        "scanned_at": datetime.now().astimezone().isoformat(timespec="seconds"),
        "scope": "Comprobaciones pasivas HTTP GET; sin autenticación ni explotación.",
        "wordpress": {"detected": False, "version": None, "version_evidence": []},
        "http": {},
        "generators": [],
        "plugins": [],
        "themes": [],
        "asset_versions": [],
        "rest_api": {"available": False, "namespaces": [], "name": None, "description": None},
        "checks": [],
        "findings": [],
        "errors": [],
    }

    def log(msg):
        if log_callback:
            log_callback(msg)

    def check(path, label):
        url = urljoin(base_url + "/", path.lstrip("/"))
        log(f"GET {url}")
        resp = safe_get(session, url)
        if isinstance(resp, dict):
            result["errors"].append({"url": url, "error": resp["error"]})
            item = {"name": label, "url": url, "status": None, "error": resp["error"]}
        else:
            item = {
                "name": label, "url": url, "status": resp.status_code,
                "content_type": resp.headers.get("Content-Type", ""),
                "final_url": resp.url,
                "bytes": len(resp.content),
            }
        result["checks"].append(item)
        return resp

    # Página principal
    home = safe_get(session, base_url)
    if isinstance(home, dict):
        result["errors"].append({"url": base_url, "error": home["error"]})
        raise RuntimeError(f"No se pudo conectar: {home['error']}")
    result["http"] = {
        "status": home.status_code,
        "final_url": home.url,
        "server": home.headers.get("Server"),
        "x_powered_by": home.headers.get("X-Powered-By"),
        "content_type": home.headers.get("Content-Type"),
        "headers": {
            k: home.headers.get(k) for k in (
                "Server", "X-Powered-By", "X-Frame-Options",
                "X-Content-Type-Options", "Referrer-Policy",
                "Content-Security-Policy", "Strict-Transport-Security",
                "Permissions-Policy"
            ) if home.headers.get(k)
        }
    }
    html = home.text[:5_000_000]
    parser = AssetParser()
    try:
        parser.feed(html)
    except Exception:
        pass

    # Indicadores de WordPress
    indicators = [
        "wp-content", "wp-includes", "wp-json", "wp-emoji-release",
        "wordpress"
    ]
    found_indicators = [x for x in indicators if x in html.lower()]
    if found_indicators or "/wp-json/" in home.url:
        result["wordpress"]["detected"] = True
        result["wordpress"]["indicators"] = found_indicators

    for generator in parser.generators:
        unique_append(result["generators"], generator)
        match = re.search(r"wordpress\s+([0-9.]+)", generator, re.I)
        if match:
            result["wordpress"]["version"] = match.group(1)
            result["wordpress"]["version_evidence"].append(
                {"source": "meta generator", "value": match.group(1), "confidence": "alta"}
            )

    # API REST pública
    api = check("/wp-json/", "API REST de WordPress")
    if not isinstance(api, dict) and api.status_code == 200:
        try:
            data = api.json()
            if isinstance(data, dict) and ("namespaces" in data or "routes" in data):
                result["wordpress"]["detected"] = True
                result["rest_api"]["available"] = True
                result["rest_api"]["namespaces"] = data.get("namespaces", [])
                result["rest_api"]["name"] = data.get("name")
                result["rest_api"]["description"] = data.get("description")
                for ns in result["rest_api"]["namespaces"]:
                    low = ns.lower()
                    for slug, friendly in KNOWN_PLUGINS.items():
                        if slug in low:
                            unique_append(result["plugins"], friendly)
                    if "generatepress" in low:
                        unique_append(result["themes"], "GeneratePress")
                    if "generateblocks" in low:
                        unique_append(result["plugins"], "GenerateBlocks")
        except (ValueError, requests.RequestException):
            pass

    # Readme: a veces contiene versión exacta, pero puede estar retirado o modificado
    readme = check("/readme.html", "readme.html")
    if not isinstance(readme, dict) and readme.status_code == 200:
        v = version_from_text(readme.text)
        if v:
            result["wordpress"]["version"] = result["wordpress"]["version"] or v
            result["wordpress"]["version_evidence"].append(
                {"source": "readme.html", "value": v, "confidence": "media; comprobar que no sea un archivo antiguo"}
            )

    # License: solo disponibilidad, normalmente no revela versión
    check("/license.txt", "license.txt")

    # Feed y XML-RPC: comprobación GET no destructiva
    feed = check("/feed/", "Feed RSS")
    if not isinstance(feed, dict) and feed.status_code == 200:
        gen = re.search(r"<generator>(.*?)</generator>", feed.text, re.I | re.S)
        if gen:
            value = re.sub(r"<[^>]+>", "", gen.group(1)).strip()
            unique_append(result["generators"], value)
            v = version_from_text(value)
            if v:
                result["wordpress"]["version"] = result["wordpress"]["version"] or v
                result["wordpress"]["version_evidence"].append(
                    {"source": "feed generator", "value": v, "confidence": "media"}
                )

    xmlrpc = check("/xmlrpc.php", "XML-RPC (GET)")
    if not isinstance(xmlrpc, dict):
        result["checks"][-1]["interpretation"] = (
            "Respuesta observada a GET; no confirma que los métodos XML-RPC estén habilitados."
        )

    check("/wp-login.php", "Página de acceso habitual")
    check("/wp-admin/", "Ruta wp-admin")
    check("/wp-cron.php", "wp-cron.php (GET)")

    # Detección de rutas de assets y versiones
    all_assets = list(parser.assets)
    # Buscar rutas referenciadas en HTML, también con comillas simples
    for match in re.findall(r"""(?:src|href)\s*=\s*['"]([^'"]+)['"]""", html, re.I):
        if any(x in match.lower() for x in ("wp-content", "wp-includes", "wp-admin")):
            unique_append(all_assets, match)

    plugin_slugs = set()
    theme_slugs = set()
    version_map = {}
    for asset in all_assets:
        absolute = urljoin(base_url + "/", asset)
        parsed = urlparse(absolute)
        path = parsed.path
        low = path.lower()
        m = re.search(r"/wp-content/plugins/([^/]+)", low)
        if m:
            slug = m.group(1)
            plugin_slugs.add(slug)
        m = re.search(r"/wp-content/themes/([^/]+)", low)
        if m:
            theme_slugs.add(m.group(1))
        q = parse_qs(parsed.query)
        for ver in q.get("ver", []):
            if re.fullmatch(r"[0-9]+(?:\.[0-9]+){0,3}", ver):
                key = f"{path}?ver={ver}"
                unique_append(result["asset_versions"], key)
                if "/wp-includes/" in low:
                    version_map.setdefault(ver, []).append(path)

    for slug in sorted(plugin_slugs):
        friendly = KNOWN_PLUGINS.get(slug, slug.replace("-", " ").title())
        unique_append(result["plugins"], friendly)
    for slug in sorted(theme_slugs):
        friendly = KNOWN_THEMES.get(slug, slug.replace("-", " ").title())
        unique_append(result["themes"], friendly)

    # Versiones de recursos del núcleo: indicios, no prueba concluyente
    for ver, paths in sorted(version_map.items()):
        if ver == "0":
            continue
        if ver not in ("3.7.1",):  # evitar confundir jQuery con WordPress
            result["wordpress"]["version_evidence"].append({
                "source": "parámetro ver de recurso wp-includes",
                "value": ver,
                "paths": paths[:5],
                "confidence": "baja; puede ser versión de recurso o caché"
            })

    if result["wordpress"]["detected"]:
        result["findings"].append({
            "severity": "info",
            "title": "WordPress identificado",
            "detail": "Se han encontrado indicadores compatibles con WordPress."
        })
    if result["rest_api"]["available"]:
        result["findings"].append({
            "severity": "info",
            "title": "API REST accesible públicamente",
            "detail": f"Se han publicado {len(result['rest_api']['namespaces'])} espacios de nombres. Esto no implica por sí solo una vulnerabilidad."
        })
    if result["plugins"]:
        result["findings"].append({
            "severity": "info",
            "title": "Plugins identificables",
            "detail": "Se han reconocido componentes a partir de rutas o namespaces: " + ", ".join(result["plugins"])
        })
    if result["themes"]:
        result["findings"].append({
            "severity": "info",
            "title": "Temas identificables",
            "detail": "Se han reconocido temas a partir de rutas o namespaces: " + ", ".join(result["themes"])
        })
    if not result["wordpress"]["version"]:
        result["findings"].append({
            "severity": "warning",
            "title": "Versión exacta no identificada",
            "detail": "No se ha encontrado una evidencia pública suficientemente fiable. Los parámetros ver= pueden pertenecer a jQuery, plugins, temas o recursos cacheados."
        })
    else:
        result["findings"].append({
            "severity": "info",
            "title": "Posible versión de WordPress",
            "detail": f"Versión candidata: {result['wordpress']['version']}. Revisa la evidencia y su nivel de confianza."
        })

    # Cabeceras defensivas: informar de ausencia sin afirmar vulnerabilidad
    security_headers = {
        "Strict-Transport-Security": "HSTS",
        "Content-Security-Policy": "CSP",
        "X-Content-Type-Options": "X-Content-Type-Options",
        "Referrer-Policy": "Referrer-Policy",
        "X-Frame-Options": "X-Frame-Options",
    }
    missing = [label for header, label in security_headers.items() if not home.headers.get(header)]
    if missing:
        result["findings"].append({
            "severity": "review",
            "title": "Cabeceras de seguridad no observadas",
            "detail": ", ".join(missing) + ". Su ausencia en esta respuesta merece revisión, pero no demuestra por sí sola una vulnerabilidad."
        })

    return result


class App(tk.Tk):
    def __init__(self):
        super().__init__()
        self.title(APP_TITLE)
        self.geometry("1120x760")
        self.minsize(900, 620)
        self.results = None
        self.worker_queue = queue.Queue()
        self._build()
        self.after(150, self._poll_queue)

    def _build(self):
        root = ttk.Frame(self, padding=14)
        root.pack(fill="both", expand=True)

        header = ttk.Frame(root)
        header.pack(fill="x")
        ttk.Label(header, text="WordPress OSINT Inspector", font=("Arial", 20, "bold")).pack(anchor="w")
        ttk.Label(
            header,
            text="Reconocimiento pasivo de WordPress, plugins, temas, API REST y exposición tecnológica.",
        ).pack(anchor="w", pady=(3, 12))

        entryrow = ttk.Frame(root)
        entryrow.pack(fill="x", pady=(0, 10))
        ttk.Label(entryrow, text="Dominio:").pack(side="left")
        self.domain_var = tk.StringVar(value="https://www.example.com")
        self.domain_entry = ttk.Entry(entryrow, textvariable=self.domain_var, font=("Arial", 12))
        self.domain_entry.pack(side="left", fill="x", expand=True, padx=8)
        self.scan_button = ttk.Button(entryrow, text="Analizar", command=self.start_scan)
        self.scan_button.pack(side="left")
        self.export_txt = ttk.Button(entryrow, text="Exportar TXT", command=self.save_txt, state="disabled")
        self.export_txt.pack(side="left", padx=(8, 0))
        self.export_json = ttk.Button(entryrow, text="Exportar JSON", command=self.save_json, state="disabled")
        self.export_json.pack(side="left", padx=(8, 0))

        self.status_var = tk.StringVar(value="Listo. Analiza únicamente dominios sobre los que tengas autorización.")
        ttk.Label(root, textvariable=self.status_var).pack(anchor="w", pady=(0, 6))
        self.progress = ttk.Progressbar(root, mode="indeterminate")
        self.progress.pack(fill="x", pady=(0, 10))

        paned = ttk.Panedwindow(root, orient="horizontal")
        paned.pack(fill="both", expand=True)

        left = ttk.Frame(paned, padding=(0, 0, 8, 0))
        right = ttk.Frame(paned)
        paned.add(left, weight=3)
        paned.add(right, weight=2)

        ttk.Label(left, text="Informe de auditoría", font=("Arial", 12, "bold")).pack(anchor="w")
        self.output = tk.Text(left, wrap="word", font=("Menlo", 10), padx=10, pady=10)
        self.output.pack(fill="both", expand=True, pady=(6, 0))
        self.output.insert("1.0", "Introduce un dominio y pulsa Analizar.\n\n"
            "La aplicación utiliza peticiones HTTP GET y no realiza pruebas de explotación.\n")
        self.output.configure(state="disabled")

        ttk.Label(right, text="Actividad", font=("Arial", 12, "bold")).pack(anchor="w")
        self.log = tk.Text(right, wrap="word", font=("Menlo", 9), padx=8, pady=8)
        self.log.pack(fill="both", expand=True, pady=(6, 0))
        self.log.configure(state="disabled")

        footer = ttk.Label(
            root,
            text="Nota: la identificación de versiones puede ser inconcluyente si el sitio oculta datos, usa caché o modifica sus recursos.",
            foreground="#555"
        )
        footer.pack(anchor="w", pady=(9, 0))

    def append_log(self, message):
        self.worker_queue.put(("log", message))

    def start_scan(self):
        domain = self.domain_var.get().strip()
        if not domain:
            messagebox.showwarning("Dominio", "Introduce un dominio.")
            return
        self.scan_button.configure(state="disabled")
        self.export_txt.configure(state="disabled")
        self.export_json.configure(state="disabled")
        self.results = None
        self.status_var.set("Analizando...")
        self.progress.start(10)
        self._set_text(self.output, "Análisis en curso...\n")
        self._set_text(self.log, "")
        threading.Thread(target=self._worker, args=(domain,), daemon=True).start()

    def _worker(self, domain):
        try:
            result = inspect_domain(domain, self.append_log)
            self.worker_queue.put(("done", result))
        except Exception as exc:
            self.worker_queue.put(("error", str(exc)))

    def _poll_queue(self):
        try:
            while True:
                kind, payload = self.worker_queue.get_nowait()
                if kind == "log":
                    self.log.configure(state="normal")
                    self.log.insert("end", payload + "\n")
                    self.log.see("end")
                    self.log.configure(state="disabled")
                elif kind == "done":
                    self.results = payload
                    self.progress.stop()
                    self.scan_button.configure(state="normal")
                    self.export_txt.configure(state="normal")
                    self.export_json.configure(state="normal")
                    self.status_var.set("Análisis finalizado.")
                    self._set_text(self.output, self.format_report(payload))
                elif kind == "error":
                    self.progress.stop()
                    self.scan_button.configure(state="normal")
                    self.status_var.set("El análisis no pudo completarse.")
                    messagebox.showerror("Error de análisis", payload)
        except queue.Empty:
            pass
        self.after(150, self._poll_queue)

    def _set_text(self, widget, value):
        widget.configure(state="normal")
        widget.delete("1.0", "end")
        widget.insert("1.0", value)
        widget.configure(state="disabled")

    def format_report(self, r):
        lines = []
        lines.append("=" * 76)
        lines.append("INFORME WORDPRESS OSINT")
        lines.append("=" * 76)
        lines.append(f"Objetivo: {r['target']}")
        lines.append(f"Fecha: {r['scanned_at']}")
        lines.append(f"Alcance: {r['scope']}")
        lines.append("")
        lines.append("[1] IDENTIFICACIÓN")
        lines.append(f"WordPress detectado: {'SÍ' if r['wordpress']['detected'] else 'NO CONFIRMADO'}")
        lines.append(f"Versión candidata: {r['wordpress']['version'] or 'No identificada'}")
        if r["wordpress"].get("indicators"):
            lines.append("Indicadores: " + ", ".join(r["wordpress"]["indicators"]))
        if r["wordpress"]["version_evidence"]:
            lines.append("Evidencias de versión:")
            for ev in r["wordpress"]["version_evidence"]:
                lines.append(f"  - {ev['source']}: {ev['value']} [{ev['confidence']}]")
        lines.append("")
        lines.append("[2] SERVIDOR Y CABECERAS")
        for k, v in r["http"].items():
            if k == "headers":
                lines.append("Cabeceras observadas:")
                for hk, hv in v.items():
                    lines.append(f"  - {hk}: {hv}")
            else:
                lines.append(f"{k}: {v}")
        lines.append("")
        lines.append("[3] GENERADORES")
        lines.extend([f"  - {x}" for x in r["generators"]] or ["  - No identificados"])
        lines.append("")
        lines.append("[4] PLUGINS IDENTIFICADOS")
        lines.extend([f"  - {x}" for x in sorted(set(r["plugins"]))] or ["  - No identificados"])
        lines.append("")
        lines.append("[5] TEMAS IDENTIFICADOS")
        lines.extend([f"  - {x}" for x in sorted(set(r["themes"]))] or ["  - No identificados"])
        lines.append("")
        lines.append("[6] API REST")
        lines.append(f"Disponible: {'SÍ' if r['rest_api']['available'] else 'No confirmada'}")
        lines.append(f"Nombre del sitio: {r['rest_api']['name']}")
        lines.append(f"Descripción: {r['rest_api']['description']}")
        lines.append(f"Namespaces ({len(r['rest_api']['namespaces'])}):")
        lines.extend([f"  - {x}" for x in r["rest_api"]["namespaces"]] or ["  - Ninguno"])
        lines.append("")
        lines.append("[7] VERSIONES EN RECURSOS")
        lines.extend([f"  - {x}" for x in r["asset_versions"]] or ["  - No encontradas"])
        lines.append("")
        lines.append("[8] COMPROBACIONES HTTP")
        for c in r["checks"]:
            lines.append(f"  - {c['name']}: HTTP {c.get('status')} | {c['url']}")
            if c.get("interpretation"):
                lines.append(f"      {c['interpretation']}")
        lines.append("")
        lines.append("[9] HALLAZGOS Y RECOMENDACIONES")
        for f in r["findings"]:
            lines.append(f"  [{f['severity'].upper()}] {f['title']}")
            lines.append(f"      {f['detail']}")
        if r["errors"]:
            lines.append("")
            lines.append("[10] ERRORES")
            for e in r["errors"]:
                lines.append(f"  - {e['url']}: {e['error']}")
        lines.append("")
        lines.append("LIMITACIONES")
        lines.append("- Un resultado HTTP 200 no significa que una función sea vulnerable.")
        lines.append("- Los parámetros ver= pueden corresponder a jQuery, plugins, temas o caché.")
        lines.append("- Los namespaces de la API identifican componentes, no sus versiones ni su estado de seguridad.")
        lines.append("- No se realizan pruebas de explotación ni comprobaciones autenticadas.")
        return "\n".join(lines)

    def save_txt(self):
        if not self.results:
            return
        path = filedialog.asksaveasfilename(
            defaultextension=".txt",
            filetypes=[("Texto", "*.txt")],
            initialfile="informe_wordpress_osint.txt"
        )
        if path:
            with open(path, "w", encoding="utf-8") as f:
                f.write(self.format_report(self.results))
            messagebox.showinfo("Exportación", f"Informe guardado en:\n{path}")

    def save_json(self):
        if not self.results:
            return
        path = filedialog.asksaveasfilename(
            defaultextension=".json",
            filetypes=[("JSON", "*.json")],
            initialfile="informe_wordpress_osint.json"
        )
        if path:
            with open(path, "w", encoding="utf-8") as f:
                json.dump(self.results, f, indent=2, ensure_ascii=False)
            messagebox.showinfo("Exportación", f"JSON guardado en:\n{path}")


if __name__ == "__main__":
    App().mainloop()

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

396

397

398

399

400

401

402

403

404

405

406

407

408

409

410

411

412

413

414

415

416

417

418

419

420

421

422

423

424

425

426

427

428

429

430

431

432

433

434

435

436

437

438

439

440

441

442

443

444

445

446

447

448

449

450

451

452

453

454

455

456

457

458

459

460

461

462

463

464

465

466

467

468

469

470

471

472

473

474

475

476

477

478

479

480

481

482

483

484

485

486

487

488

489

490

491

492

493

494

495

496

497

498

499

500

501

502

503

504

505

506

507

508

509

510

511

512

513

514

515

516

517

518

519

520

521

522

523

524

525

526

527

528

529

530

531

532

533

534

535

536

537

538

539

540

541

542

543

544

545

546

547

548

549

550

551

552

553

554

555

556

557

558

559

560

561

562

563

564

565

566

567

568

569

570

571

572

573

574

575

576

577

578

579

580

581

582

583

584

585

586

587

588

589

590

591

592

593

594

595

596

597

598

599

600

601

602

#!/usr/bin/env python3

# -*- coding: utf-8 -*-

"""

WordPress OSINT Inspector

Auditoría pasiva de tecnologías WordPress mediante peticiones HTTP GET.

No realiza autenticación, POST, explotación ni modificación del servidor.

"""

import json

import re

import threading

import queue

import time

from datetime import datetime

from urllib.parse import urljoin, urlparse, parse_qs

from html.parser import HTMLParser

import tkinter as tk

from tkinter import ttk, messagebox, filedialog

try:

import requests

except ImportError:

raise SystemExit("Falta requests. Instala las dependencias con: python3 -m pip install -r requirements.txt")

APP_TITLE = "WordPress OSINT Inspector"

USER_AGENT = "WordPressOSINTInspector/1.0 (+passive security assessment)"

TIMEOUT = 12

KNOWN_PLUGINS = {

"wp-rocket": "WP Rocket",

"wordfence": "Wordfence",

"wordfence-login-security": "Wordfence Login Security",

"sg-security": "SiteGround Security",

"wordpress-seo": "Yoast SEO",

"wpforms": "WPForms",

"generateblocks": "GenerateBlocks",

"generateblocks-pro": "GenerateBlocks Pro",

"generatepress-pro": "GeneratePress Premium",

"advanced-database-cleaner": "Advanced Database Cleaner",

"all-in-one-wp-security": "All In One WP Security",

"really-simple-ssl": "Really Simple Security",

"elementor": "Elementor",

"contact-form-7": "Contact Form 7",

"woocommerce": "WooCommerce",

"akismet": "Akismet",

"jetpack": "Jetpack",

"updraftplus": "UpdraftPlus",

"ithemes-security": "Solid Security",

}

KNOWN_THEMES = {

"generatepress": "GeneratePress",

"astra": "Astra",

"hello-elementor": "Hello Elementor",

"oceanwp": "OceanWP",

"kadence": "Kadence",

"blocksy": "Blocksy",

"divi": "Divi",

"flatsome": "Flatsome",

"avada": "Avada",

}

class AssetParser(HTMLParser):

def __init__(self):

super().__init__()

self.assets = []

self.generators = []

self.links = []

def handle_starttag(self, tag, attrs):

a = dict(attrs)

if tag.lower() == "meta" and a.get("name", "").lower() == "generator":

if a.get("content"):

self.generators.append(a["content"])

for key in ("src", "href"):

value = a.get(key)

if value and any(x in value.lower() for x in (

"wp-content", "wp-includes", "wp-admin"

)):

self.assets.append(value)

if tag.lower() == "link" and a.get("rel", "").lower() in ("https://api.w.org/", "api.w.org/"):

if a.get("href"):

self.links.append(a["href"])

def normalize_domain(value):

value = value.strip()

if not value:

raise ValueError("Introduce un dominio.")

if not re.match(r"^https?://", value, re.I):

value = "https://" + value

parsed = urlparse(value)

if not parsed.hostname:

raise ValueError("Dominio no válido.")

if parsed.scheme not in ("http", "https"):

raise ValueError("Solo se admiten HTTP y HTTPS.")

return f"{parsed.scheme}://{parsed.netloc}"

def safe_get(session, url):

try:

response = session.get(url, timeout=TIMEOUT, allow_redirects=True)

return response

except requests.RequestException as exc:

return {"error": str(exc)}

def version_from_text(text):

patterns = [

r"(?im)^\s*Version\s+([0-9]+(?:\.[0-9]+){1,3})",

r"(?i)wordpress\s+([0-9]+(?:\.[0-9]+){1,3})",

]

for pattern in patterns:

match = re.search(pattern, text or "")

if match:

return match.group(1)

return None

def unique_append(items, value):

if value and value not in items:

items.append(value)

def inspect_domain(domain, log_callback=None):

base_url = normalize_domain(domain)

session = requests.Session()

session.headers.update({"User-Agent": USER_AGENT, "Accept": "*/*"})

result = {

"target": base_url,

"scanned_at": datetime.now().astimezone().isoformat(timespec="seconds"),

"scope": "Comprobaciones pasivas HTTP GET; sin autenticación ni explotación.",

"wordpress": {"detected": False, "version": None, "version_evidence": []},

"http": {},

"generators": [],

"plugins": [],

"themes": [],

"asset_versions": [],

"rest_api": {"available": False, "namespaces": [], "name": None, "description": None},

"checks": [],

"findings": [],

"errors": [],

}

def log(msg):

if log_callback:

log_callback(msg)

def check(path, label):

url = urljoin(base_url + "/", path.lstrip("/"))

log(f"GET {url}")

resp = safe_get(session, url)

if isinstance(resp, dict):

result["errors"].append({"url": url, "error": resp["error"]})

item = {"name": label, "url": url, "status": None, "error": resp["error"]}

else:

item = {

"name": label, "url": url, "status": resp.status_code,

"content_type": resp.headers.get("Content-Type", ""),

"final_url": resp.url,

"bytes": len(resp.content),

}

result["checks"].append(item)

return resp

# Página principal

home = safe_get(session, base_url)

if isinstance(home, dict):

result["errors"].append({"url": base_url, "error": home["error"]})

raise RuntimeError(f"No se pudo conectar: {home['error']}")

result["http"] = {

"status": home.status_code,

"final_url": home.url,

"server": home.headers.get("Server"),

"x_powered_by": home.headers.get("X-Powered-By"),

"content_type": home.headers.get("Content-Type"),

"headers": {

k: home.headers.get(k) for k in (

"Server", "X-Powered-By", "X-Frame-Options",

"X-Content-Type-Options", "Referrer-Policy",

"Content-Security-Policy", "Strict-Transport-Security",

"Permissions-Policy"

) if home.headers.get(k)

}

html = home.text[:5_000_000]

parser = AssetParser()

try:

parser.feed(html)

except Exception:

pass

# Indicadores de WordPress

indicators = [

"wp-content", "wp-includes", "wp-json", "wp-emoji-release",

"wordpress"

]

found_indicators = [x for x in indicators if x in html.lower()]

if found_indicators or "/wp-json/" in home.url:

result["wordpress"]["detected"] = True

result["wordpress"]["indicators"] = found_indicators

for generator in parser.generators:

unique_append(result["generators"], generator)

match = re.search(r"wordpress\s+([0-9.]+)", generator, re.I)

if match:

result["wordpress"]["version"] = match.group(1)

result["wordpress"]["version_evidence"].append(

{"source": "meta generator", "value": match.group(1), "confidence": "alta"}

)

# API REST pública

api = check("/wp-json/", "API REST de WordPress")

if not isinstance(api, dict) and api.status_code == 200:

try:

data = api.json()

if isinstance(data, dict) and ("namespaces" in data or "routes" in data):

result["wordpress"]["detected"] = True

result["rest_api"]["available"] = True

result["rest_api"]["namespaces"] = data.get("namespaces", [])

result["rest_api"]["name"] = data.get("name")

result["rest_api"]["description"] = data.get("description")

for ns in result["rest_api"]["namespaces"]:

low = ns.lower()

for slug, friendly in KNOWN_PLUGINS.items():

if slug in low:

unique_append(result["plugins"], friendly)

if "generatepress" in low:

unique_append(result["themes"], "GeneratePress")

if "generateblocks" in low:

unique_append(result["plugins"], "GenerateBlocks")

except (ValueError, requests.RequestException):

pass

# Readme: a veces contiene versión exacta, pero puede estar retirado o modificado

readme = check("/readme.html", "readme.html")

if not isinstance(readme, dict) and readme.status_code == 200:

v = version_from_text(readme.text)

if v:

result["wordpress"]["version"] = result["wordpress"]["version"] or v

result["wordpress"]["version_evidence"].append(

{"source": "readme.html", "value": v, "confidence": "media; comprobar que no sea un archivo antiguo"}

)

# License: solo disponibilidad, normalmente no revela versión

check("/license.txt", "license.txt")

# Feed y XML-RPC: comprobación GET no destructiva

feed = check("/feed/", "Feed RSS")

if not isinstance(feed, dict) and feed.status_code == 200:

gen = re.search(r"<generator>(.*?)</generator>", feed.text, re.I | re.S)

if gen:

value = re.sub(r"<[^>]+>", "", gen.group(1)).strip()

unique_append(result["generators"], value)

v = version_from_text(value)

if v:

result["wordpress"]["version"] = result["wordpress"]["version"] or v

result["wordpress"]["version_evidence"].append(

{"source": "feed generator", "value": v, "confidence": "media"}

)

xmlrpc = check("/xmlrpc.php", "XML-RPC (GET)")

if not isinstance(xmlrpc, dict):

result["checks"][-1]["interpretation"] = (

"Respuesta observada a GET; no confirma que los métodos XML-RPC estén habilitados."

)

check("/wp-login.php", "Página de acceso habitual")

check("/wp-admin/", "Ruta wp-admin")

check("/wp-cron.php", "wp-cron.php (GET)")

# Detección de rutas de assets y versiones

all_assets = list(parser.assets)

# Buscar rutas referenciadas en HTML, también con comillas simples

for match in re.findall(r"""(?:src|href)\s*=\s*['"]([^'"]+)['"]""", html, re.I):

if any(x in match.lower() for x in ("wp-content", "wp-includes", "wp-admin")):

unique_append(all_assets, match)

plugin_slugs = set()

theme_slugs = set()

version_map = {}

for asset in all_assets:

absolute = urljoin(base_url + "/", asset)

parsed = urlparse(absolute)

path = parsed.path

low = path.lower()

m = re.search(r"/wp-content/plugins/([^/]+)", low)

if m:

slug = m.group(1)

plugin_slugs.add(slug)

m = re.search(r"/wp-content/themes/([^/]+)", low)

if m:

theme_slugs.add(m.group(1))

q = parse_qs(parsed.query)

for ver in q.get("ver", []):

if re.fullmatch(r"[0-9]+(?:\.[0-9]+){0,3}", ver):

key = f"{path}?ver={ver}"

unique_append(result["asset_versions"], key)

if "/wp-includes/" in low:

version_map.setdefault(ver, []).append(path)

for slug in sorted(plugin_slugs):

friendly = KNOWN_PLUGINS.get(slug, slug.replace("-", " ").title())

unique_append(result["plugins"], friendly)

for slug in sorted(theme_slugs):

friendly = KNOWN_THEMES.get(slug, slug.replace("-", " ").title())

unique_append(result["themes"], friendly)

# Versiones de recursos del núcleo: indicios, no prueba concluyente

for ver, paths in sorted(version_map.items()):

if ver == "0":

continue

if ver not in ("3.7.1",): # evitar confundir jQuery con WordPress

result["wordpress"]["version_evidence"].append({

"source": "parámetro ver de recurso wp-includes",

"value": ver,

"paths": paths[:5],

"confidence": "baja; puede ser versión de recurso o caché"

})

if result["wordpress"]["detected"]:

result["findings"].append({

"severity": "info",

"title": "WordPress identificado",

"detail": "Se han encontrado indicadores compatibles con WordPress."

})

if result["rest_api"]["available"]:

result["findings"].append({

"severity": "info",

"title": "API REST accesible públicamente",

"detail": f"Se han publicado {len(result['rest_api']['namespaces'])} espacios de nombres. Esto no implica por sí solo una vulnerabilidad."

})

if result["plugins"]:

result["findings"].append({

"severity": "info",

"title": "Plugins identificables",

"detail": "Se han reconocido componentes a partir de rutas o namespaces: " + ", ".join(result["plugins"])

})

if result["themes"]:

result["findings"].append({

"severity": "info",

"title": "Temas identificables",

"detail": "Se han reconocido temas a partir de rutas o namespaces: " + ", ".join(result["themes"])

})

if not result["wordpress"]["version"]:

result["findings"].append({

"severity": "warning",

"title": "Versión exacta no identificada",

"detail": "No se ha encontrado una evidencia pública suficientemente fiable. Los parámetros ver= pueden pertenecer a jQuery, plugins, temas o recursos cacheados."

})

else:

result["findings"].append({

"severity": "info",

"title": "Posible versión de WordPress",

"detail": f"Versión candidata: {result['wordpress']['version']}. Revisa la evidencia y su nivel de confianza."

})

# Cabeceras defensivas: informar de ausencia sin afirmar vulnerabilidad

security_headers = {

"Strict-Transport-Security": "HSTS",

"Content-Security-Policy": "CSP",

"X-Content-Type-Options": "X-Content-Type-Options",

"Referrer-Policy": "Referrer-Policy",

"X-Frame-Options": "X-Frame-Options",

}

missing = [label for header, label in security_headers.items() if not home.headers.get(header)]

if missing:

result["findings"].append({

"severity": "review",

"title": "Cabeceras de seguridad no observadas",

"detail": ", ".join(missing) + ". Su ausencia en esta respuesta merece revisión, pero no demuestra por sí sola una vulnerabilidad."

})

return result

class App(tk.Tk):

def __init__(self):

super().__init__()

self.title(APP_TITLE)

self.geometry("1120x760")

self.minsize(900, 620)

self.results = None

self.worker_queue = queue.Queue()

self._build()

self.after(150, self._poll_queue)

def _build(self):

root = ttk.Frame(self, padding=14)

root.pack(fill="both", expand=True)

header = ttk.Frame(root)

header.pack(fill="x")

ttk.Label(header, text="WordPress OSINT Inspector", font=("Arial", 20, "bold")).pack(anchor="w")

ttk.Label(

header,

text="Reconocimiento pasivo de WordPress, plugins, temas, API REST y exposición tecnológica.",

).pack(anchor="w", pady=(3, 12))

entryrow = ttk.Frame(root)

entryrow.pack(fill="x", pady=(0, 10))

ttk.Label(entryrow, text="Dominio:").pack(side="left")

self.domain_var = tk.StringVar(value="https://www.example.com")

self.domain_entry = ttk.Entry(entryrow, textvariable=self.domain_var, font=("Arial", 12))

self.domain_entry.pack(side="left", fill="x", expand=True, padx=8)

self.scan_button = ttk.Button(entryrow, text="Analizar", command=self.start_scan)

self.scan_button.pack(side="left")

self.export_txt = ttk.Button(entryrow, text="Exportar TXT", command=self.save_txt, state="disabled")

self.export_txt.pack(side="left", padx=(8, 0))

self.export_json = ttk.Button(entryrow, text="Exportar JSON", command=self.save_json, state="disabled")

self.export_json.pack(side="left", padx=(8, 0))

self.status_var = tk.StringVar(value="Listo. Analiza únicamente dominios sobre los que tengas autorización.")

ttk.Label(root, textvariable=self.status_var).pack(anchor="w", pady=(0, 6))

self.progress = ttk.Progressbar(root, mode="indeterminate")

self.progress.pack(fill="x", pady=(0, 10))

paned = ttk.Panedwindow(root, orient="horizontal")

paned.pack(fill="both", expand=True)

left = ttk.Frame(paned, padding=(0, 0, 8, 0))

right = ttk.Frame(paned)

paned.add(left, weight=3)

paned.add(right, weight=2)

ttk.Label(left, text="Informe de auditoría", font=("Arial", 12, "bold")).pack(anchor="w")

self.output = tk.Text(left, wrap="word", font=("Menlo", 10), padx=10, pady=10)

self.output.pack(fill="both", expand=True, pady=(6, 0))

self.output.insert("1.0", "Introduce un dominio y pulsa Analizar.\n\n"

"La aplicación utiliza peticiones HTTP GET y no realiza pruebas de explotación.\n")

self.output.configure(state="disabled")

ttk.Label(right, text="Actividad", font=("Arial", 12, "bold")).pack(anchor="w")

self.log = tk.Text(right, wrap="word", font=("Menlo", 9), padx=8, pady=8)

self.log.pack(fill="both", expand=True, pady=(6, 0))

self.log.configure(state="disabled")

footer = ttk.Label(

root,

text="Nota: la identificación de versiones puede ser inconcluyente si el sitio oculta datos, usa caché o modifica sus recursos.",

foreground="#555"

)

footer.pack(anchor="w", pady=(9, 0))

def append_log(self, message):

self.worker_queue.put(("log", message))

def start_scan(self):

domain = self.domain_var.get().strip()

if not domain:

messagebox.showwarning("Dominio", "Introduce un dominio.")

return

self.scan_button.configure(state="disabled")

self.export_txt.configure(state="disabled")

self.export_json.configure(state="disabled")

self.results = None

self.status_var.set("Analizando...")

self.progress.start(10)

self._set_text(self.output, "Análisis en curso...\n")

self._set_text(self.log, "")

threading.Thread(target=self._worker, args=(domain,), daemon=True).start()

def _worker(self, domain):

try:

result = inspect_domain(domain, self.append_log)

self.worker_queue.put(("done", result))

except Exception as exc:

self.worker_queue.put(("error", str(exc)))

def _poll_queue(self):

try:

while True:

kind, payload = self.worker_queue.get_nowait()

if kind == "log":

self.log.configure(state="normal")

self.log.insert("end", payload + "\n")

self.log.see("end")

self.log.configure(state="disabled")

elif kind == "done":

self.results = payload

self.progress.stop()

self.scan_button.configure(state="normal")

self.export_txt.configure(state="normal")

self.export_json.configure(state="normal")

self.status_var.set("Análisis finalizado.")

self._set_text(self.output, self.format_report(payload))

elif kind == "error":

self.progress.stop()

self.scan_button.configure(state="normal")

self.status_var.set("El análisis no pudo completarse.")

messagebox.showerror("Error de análisis", payload)

except queue.Empty:

pass

self.after(150, self._poll_queue)

def _set_text(self, widget, value):

widget.configure(state="normal")

widget.delete("1.0", "end")

widget.insert("1.0", value)

widget.configure(state="disabled")

def format_report(self, r):

lines = []

lines.append("=" * 76)

lines.append("INFORME WORDPRESS OSINT")

lines.append("=" * 76)

lines.append(f"Objetivo: {r['target']}")

lines.append(f"Fecha: {r['scanned_at']}")

lines.append(f"Alcance: {r['scope']}")

lines.append("")

lines.append("[1] IDENTIFICACIÓN")

lines.append(f"WordPress detectado: {'SÍ' if r['wordpress']['detected'] else 'NO CONFIRMADO'}")

lines.append(f"Versión candidata: {r['wordpress']['version'] or 'No identificada'}")

if r["wordpress"].get("indicators"):

lines.append("Indicadores: " + ", ".join(r["wordpress"]["indicators"]))

if r["wordpress"]["version_evidence"]:

lines.append("Evidencias de versión:")

for ev in r["wordpress"]["version_evidence"]:

lines.append(f" - {ev['source']}: {ev['value']} [{ev['confidence']}]")

lines.append("")

lines.append("[2] SERVIDOR Y CABECERAS")

for k, v in r["http"].items():

if k == "headers":

lines.append("Cabeceras observadas:")

for hk, hv in v.items():

lines.append(f" - {hk}: {hv}")

else:

lines.append(f"{k}: {v}")

lines.append("")

lines.append("[3] GENERADORES")

lines.extend([f" - {x}" for x in r["generators"]] or [" - No identificados"])

lines.append("")

lines.append("[4] PLUGINS IDENTIFICADOS")

lines.extend([f" - {x}" for x in sorted(set(r["plugins"]))] or [" - No identificados"])

lines.append("")

lines.append("[5] TEMAS IDENTIFICADOS")

lines.extend([f" - {x}" for x in sorted(set(r["themes"]))] or [" - No identificados"])

lines.append("")

lines.append("[6] API REST")

lines.append(f"Disponible: {'SÍ' if r['rest_api']['available'] else 'No confirmada'}")

lines.append(f"Nombre del sitio: {r['rest_api']['name']}")

lines.append(f"Descripción: {r['rest_api']['description']}")

lines.append(f"Namespaces ({len(r['rest_api']['namespaces'])}):")

lines.extend([f" - {x}" for x in r["rest_api"]["namespaces"]] or [" - Ninguno"])

lines.append("")

lines.append("[7] VERSIONES EN RECURSOS")

lines.extend([f" - {x}" for x in r["asset_versions"]] or [" - No encontradas"])

lines.append("")

lines.append("[8] COMPROBACIONES HTTP")

for c in r["checks"]:

lines.append(f" - {c['name']}: HTTP {c.get('status')} | {c['url']}")

if c.get("interpretation"):

lines.append(f" {c['interpretation']}")

lines.append("")

lines.append("[9] HALLAZGOS Y RECOMENDACIONES")

for f in r["findings"]:

lines.append(f" [{f['severity'].upper()}] {f['title']}")

lines.append(f" {f['detail']}")

if r["errors"]:

lines.append("")

lines.append("[10] ERRORES")

for e in r["errors"]:

lines.append(f" - {e['url']}: {e['error']}")

lines.append("")

lines.append("LIMITACIONES")

lines.append("- Un resultado HTTP 200 no significa que una función sea vulnerable.")

lines.append("- Los parámetros ver= pueden corresponder a jQuery, plugins, temas o caché.")

lines.append("- Los namespaces de la API identifican componentes, no sus versiones ni su estado de seguridad.")

lines.append("- No se realizan pruebas de explotación ni comprobaciones autenticadas.")

return "\n".join(lines)

def save_txt(self):

if not self.results:

return

path = filedialog.asksaveasfilename(

defaultextension=".txt",

filetypes=[("Texto", "*.txt")],

initialfile="informe_wordpress_osint.txt"

)

if path:

with open(path, "w", encoding="utf-8") as f:

f.write(self.format_report(self.results))

messagebox.showinfo("Exportación", f"Informe guardado en:\n{path}")

def save_json(self):

if not self.results:

return

path = filedialog.asksaveasfilename(

defaultextension=".json",

filetypes=[("JSON", "*.json")],

initialfile="informe_wordpress_osint.json"

)

if path:

with open(path, "w", encoding="utf-8") as f:

json.dump(self.results, f, indent=2, ensure_ascii=False)

messagebox.showinfo("Exportación", f"JSON guardado en:\n{path}")

if __name__ == "__main__":

App().mainloop()

WordPress OSINT Inspector (Web, Python)

LIBRO DE POWERSHELL

LO ÚLTIMO

RECOMENDADO