egutierrez
935008ec3f
Añade el capability group `recon` (dominio cybersecurity + pipelines, Python),
con la política de archivado OSINT y página madre docs/capabilities/recon.md.
Lookups y sondeo (wrappers de CLI):
- whois_lookup, rdap_lookup, dns_records, ping_host, traceroute_host, nmap_scan
- save_scan_to_osint (sink común) + recon_osint (pipeline one-shot scan+archivado)
Escaneo de puertos/servicios nativo (stdlib, sin nmap ni sudo):
- scan_tcp_ports: connect-scan TCP concurrente (open/closed/filtered)
- grab_service_banner: banner grab + identificación de servicio/versión real
- identify_port_service: puro, puerto -> servicio IANA esperado (~120 puertos)
- scan_port_services: pipeline one-shot (scan -> identify + banner por puerto abierto)
Fingerprint de tecnología web (estilo Wappalyzer), patrón pura/impura:
- fetch_http_fingerprint: GET stdlib, recoge headers/html/cookies (solo nombres)
- detect_web_tech: puro, matchea ~50 firmas regex -> tecnologías por categoría
- fingerprint_web_stack: pipeline one-shot url -> tecnologías
Todas devuelven dict {status} sin lanzar. Tests: 43 verdes, sin red externa.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
109 lines
3.4 KiB
Python
109 lines
3.4 KiB
Python
"""Tests para detect_web_tech (deteccion de tecnologia web estilo Wappalyzer)."""
|
|
|
|
from detect_web_tech import detect_web_tech
|
|
|
|
|
|
def _names(result):
|
|
return {t["name"] for t in result["technologies"]}
|
|
|
|
|
|
def _by_name(result, name):
|
|
for t in result["technologies"]:
|
|
if t["name"] == name:
|
|
return t
|
|
return None
|
|
|
|
|
|
def test_nginx_por_header_con_version():
|
|
result = detect_web_tech({"server": "nginx/1.24.0"})
|
|
assert "nginx" in _names(result)
|
|
nginx = _by_name(result, "nginx")
|
|
assert nginx["version"] == "1.24.0"
|
|
assert nginx["category"] == "web-server"
|
|
assert nginx["confidence"] == "high"
|
|
|
|
|
|
def test_wordpress_por_html_y_meta_implica_php():
|
|
html = (
|
|
'<html><head>'
|
|
'<meta name="generator" content="WordPress 6.4">'
|
|
'</head><body>'
|
|
'<link href="/wp-content/themes/x/style.css">'
|
|
'</body></html>'
|
|
)
|
|
result = detect_web_tech({}, html=html)
|
|
names = _names(result)
|
|
assert "WordPress" in names
|
|
assert "PHP" in names # implied
|
|
wp = _by_name(result, "WordPress")
|
|
assert wp["version"] == "6.4"
|
|
assert wp["confidence"] == "high"
|
|
php = _by_name(result, "PHP")
|
|
assert php["confidence"] == "medium"
|
|
assert "implied by WordPress" in php["evidence"]
|
|
|
|
|
|
def test_php_por_cookie():
|
|
result = detect_web_tech({}, cookies=["PHPSESSID"])
|
|
php = _by_name(result, "PHP")
|
|
assert php is not None
|
|
assert php["category"] == "programming-language"
|
|
assert php["confidence"] == "high"
|
|
assert "PHPSESSID" in php["evidence"]
|
|
|
|
|
|
def test_cloudflare_por_header():
|
|
result = detect_web_tech({"server": "cloudflare", "cf-ray": "8a1b2c3d4e5f-MAD"})
|
|
cf = _by_name(result, "Cloudflare")
|
|
assert cf is not None
|
|
assert cf["category"] == "cdn"
|
|
assert cf["confidence"] == "high"
|
|
|
|
|
|
def test_entrada_vacia():
|
|
result = detect_web_tech({})
|
|
assert result["technologies"] == []
|
|
assert result["by_category"] == {}
|
|
assert result["count"] == 0
|
|
|
|
|
|
def test_entrada_vacia_explicita_headers_y_html():
|
|
result = detect_web_tech({}, html="", cookies=None, final_url="")
|
|
assert result["count"] == 0
|
|
assert result["technologies"] == []
|
|
|
|
|
|
def test_determinismo():
|
|
headers = {"server": "nginx/1.24.0", "x-powered-by": "PHP/8.2"}
|
|
html = '<meta name="generator" content="WordPress 6.4">wp-content'
|
|
a = detect_web_tech(headers, html=html, cookies=["PHPSESSID"])
|
|
b = detect_web_tech(headers, html=html, cookies=["PHPSESSID"])
|
|
assert a == b
|
|
|
|
|
|
def test_count_y_by_category_consistentes():
|
|
headers = {"server": "nginx/1.24.0"}
|
|
html = '<meta name="generator" content="WordPress 6.4">wp-content'
|
|
result = detect_web_tech(headers, html=html)
|
|
assert result["count"] == len(result["technologies"])
|
|
total_in_categories = sum(len(v) for v in result["by_category"].values())
|
|
assert total_in_categories == result["count"]
|
|
assert "nginx" in result["by_category"]["web-server"]
|
|
assert "WordPress" in result["by_category"]["cms"]
|
|
|
|
|
|
def test_headers_claves_mayusculas_se_normalizan():
|
|
result = detect_web_tech({"Server": "Apache/2.4.57"})
|
|
apache = _by_name(result, "Apache")
|
|
assert apache is not None
|
|
assert apache["version"] == "2.4.57"
|
|
|
|
|
|
def test_jquery_por_script_src_es_medium():
|
|
html = '<script src="/static/jquery-3.6.0.min.js"></script>'
|
|
result = detect_web_tech({}, html=html)
|
|
jq = _by_name(result, "jQuery")
|
|
assert jq is not None
|
|
assert jq["confidence"] == "medium"
|
|
assert jq["version"] == "3.6.0"
|