Neuer Befehl `python -m scanner cloak-check`: - Crawlt die Website zweimal: einmal mit Browser-UA, einmal als Googlebot - Vergleicht Text, Links und Response-Header (Vary: User-Agent) - Scoring: Bot-Only-Link 60 Pkt (RED), extra Text >100 Zeichen 40 Pkt, Vary: User-Agent ohne Inhaltsdiff 25 Pkt - Eigener Report unter reports/<ts>_cloak/ Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
113 lines
2.8 KiB
YAML
113 lines
2.8 KiB
YAML
# Integrity Scanner — Hauptkonfiguration
|
|
# Alle Werte sind optional; fehlende werden aus den Defaults übernommen.
|
|
|
|
target: "https://bredelar.info"
|
|
user_agent: "integrity-scanner/1.0 (+security-monitoring)"
|
|
request_timeout: 20
|
|
|
|
data_dir: "data"
|
|
reports_dir: "reports"
|
|
logs_dir: "logs"
|
|
config_dir: "config"
|
|
|
|
crawl:
|
|
max_pages: 200
|
|
delay_seconds: 1.0
|
|
respect_robots_txt: false
|
|
skip_extensions:
|
|
- ".jpg"
|
|
- ".jpeg"
|
|
- ".png"
|
|
- ".gif"
|
|
- ".webp"
|
|
- ".svg"
|
|
- ".ico"
|
|
- ".pdf"
|
|
- ".zip"
|
|
- ".woff"
|
|
- ".woff2"
|
|
- ".ttf"
|
|
- ".otf"
|
|
- ".eot"
|
|
- ".mp4"
|
|
- ".mp3"
|
|
- ".webm"
|
|
- ".avi"
|
|
- ".mov"
|
|
|
|
scoring:
|
|
new_external_domain: 50
|
|
new_internal_url: 30
|
|
missing_internal_url: 20
|
|
hidden_content: 40
|
|
unexpected_canonical: 35
|
|
meta_refresh: 40
|
|
unexpected_jsonld: 35
|
|
large_text_addition: 20
|
|
new_inline_script_suspicious: 30
|
|
comment_links: 25
|
|
new_broken_link: 20 # neue 4xx/5xx-Seite, die in Baseline nicht vorhanden war
|
|
suspicious_filename: 60 # Link auf Webshell-/Backdoor-typischen Dateinamen
|
|
cloaking_extra_link: 60 # Link nur im Bot-Crawl sichtbar
|
|
cloaking_extra_text: 40 # signifikant mehr Text im Bot-Crawl (>100 Zeichen)
|
|
cloaking_vary_ua: 25 # Vary: User-Agent Header (ohne sonstigen Unterschied)
|
|
|
|
thresholds:
|
|
yellow: 20 # ab diesem Score: Warnung (gelb)
|
|
red: 60 # ab diesem Score: Alarm (rot)
|
|
large_text_block_chars: 200 # Textblock ab dieser Länge wird als „groß" gewertet
|
|
|
|
alerting:
|
|
min_level: "yellow" # "yellow" oder "red"
|
|
email:
|
|
enabled: false
|
|
smtp_host: "localhost"
|
|
smtp_port: 587
|
|
smtp_tls: true
|
|
smtp_user: ""
|
|
smtp_password_env: "SCANNER_SMTP_PASSWORD" # Passwort aus Umgebungsvariable
|
|
from: "scanner@bredelar.info"
|
|
to:
|
|
- "admin@bredelar.info"
|
|
webhook:
|
|
enabled: false
|
|
url: "" # z.B. Telegram-Bot-Webhook, Slack-Incoming-Webhook
|
|
|
|
normalization:
|
|
strip_html_comments: true
|
|
collapse_whitespace: true
|
|
# Selektoren, die vor dem Diff ignoriert werden (z.B. Datums-/Cache-Elemente)
|
|
ignore_selectors:
|
|
# - "#last-modified"
|
|
# - ".timestamp"
|
|
# Regex-Muster im Text, die vor dem Diff entfernt werden
|
|
ignore_patterns:
|
|
# - '\d{1,2}\.\d{1,2}\.\d{4}' # Datumsangaben
|
|
# - 'Stand:\s+\S+'
|
|
|
|
# Erlaubte @type-Werte in JSON-LD (alles andere löst Alarm aus)
|
|
allowed_jsonld_types:
|
|
- "Organization"
|
|
- "WebSite"
|
|
- "WebPage"
|
|
- "Article"
|
|
- "BreadcrumbList"
|
|
- "ItemList"
|
|
- "LocalBusiness"
|
|
- "Place"
|
|
- "Person"
|
|
- "Event"
|
|
- "FAQPage"
|
|
- "Question"
|
|
- "Answer"
|
|
- "ImageObject"
|
|
- "SiteLinksSearchBox"
|
|
- "ContactPage"
|
|
- "AboutPage"
|
|
|
|
# Security-Header, die auf jeder Seite erwartet werden
|
|
security_headers:
|
|
- "Content-Security-Policy"
|
|
- "Strict-Transport-Security"
|
|
- "X-Content-Type-Options"
|
|
- "Referrer-Policy"
|