# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.
# use:      how AI systems may consume the content (immediate, reference, or full).

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content


User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

User-agent: *
# public
Allow: /
Allow: /forum
Allow: /rules
Allow: /contact
Allow: /about
Allow: /login
Allow: /register

# staff panel — do not crawl
Disallow: /panel/
Disallow: /panel/roster
Disallow: /panel/member/
Disallow: /panel/search
Disallow: /panel/inbox/
Disallow: /panel/pm/
Disallow: /panel/donations
Disallow: /panel/donation/
Disallow: /panel/escrow

# staff-only (intentionally exposed)
Disallow: /staff/
Disallow: /staff/meetings
Disallow: /staff/meeting/
Disallow: /staff/invite-tree
Disallow: /staff/modlog
Disallow: /staff/tickets
Disallow: /staff/ticket/

# market board
Disallow: /m/
Disallow: /m/board
Disallow: /m/listing/

# intel feed (leaks + pastes + breaches + databases + combos + cracking + tutorials)
Disallow: /intel/
Disallow: /intel/feed
Disallow: /intel/paste/
Disallow: /intel/breach/
Disallow: /intel/databases
Disallow: /intel/database/
Disallow: /intel/combolists
Disallow: /intel/combolist/
Disallow: /intel/cracking
Disallow: /intel/config/
Disallow: /intel/tutorials
Disallow: /intel/tutorial/

# entities / on-chain / archive / backups
Disallow: /entities/
Disallow: /entities/registry
Disallow: /entities/scammers
Disallow: /entities/canary
Disallow: /entities/le-watch
Disallow: /entities/incidents
Disallow: /entities/incident/
Disallow: /chain/
Disallow: /chain/ledger
Disallow: /chain/address/
Disallow: /chain/tx/
Disallow: /cdn/
Disallow: /cdn/archive
Disallow: /cdn/pgp/
Disallow: /cdn/leaks/
Disallow: /cdn/feeds/
Disallow: /backup/
Disallow: /backup/db

# market
Disallow: /m/vendor/
Disallow: /m/disputes
Disallow: /m/dispute/
Disallow: /m/auctions
Disallow: /m/auction/

# operations — VortexLocker DLS mirror + broker boards (fictional, see /about)
Disallow: /ops/
Disallow: /ops/dls
Disallow: /ops/dls/
Disallow: /ops/iab
Disallow: /ops/iab/
Disallow: /ops/logs
Disallow: /ops/log/
Disallow: /ops/phishkits
Disallow: /ops/phishkit/
Disallow: /ops/exploits
Disallow: /ops/exploit/
Disallow: /ops/botnet
Disallow: /ops/wanted
Disallow: /ops/channels

# OSINT infra artefacts
Disallow: /osint/
Disallow: /osint/pdns
Disallow: /osint/pdns/
Disallow: /osint/ct
Disallow: /osint/ct/
Disallow: /osint/whois
Disallow: /osint/whois/
Disallow: /osint/hosts
Disallow: /osint/host/
Disallow: /osint/asns
Disallow: /osint/asn/
Disallow: /osint/mail
Disallow: /osint/mail/
Disallow: /osint/images
Disallow: /osint/image/

# intel timeline + STIX/MISP/IOC exports
Disallow: /intel/timeline

# admin
Disallow: /admin/
Disallow: /admin/debug

# api
Disallow: /api/v1/config
Disallow: /api/v1/admin/
Disallow: /api/v1/stix/
Disallow: /api/v1/misp/
Disallow: /api/bd/

# should not be exposed but here we are
Disallow: /.env
Disallow: /.git/
Disallow: /backup.sql
Disallow: /backup/db.sql.bak
Disallow: /.aws/
Disallow: /.npmrc
Disallow: /.dockerconfigjson
Disallow: /.DS_Store
Disallow: /.idea/
Disallow: /composer.json
Disallow: /package-lock.json
Disallow: /server-status
Disallow: /api/internal/swagger.json
Disallow: /api/v0/users
Disallow: /api/v0/
Disallow: /wp-content/uploads/

Sitemap: https://training.casusbelli.io/sitemap.xml