# 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.

# 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
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# BlackVeil Security - robots.txt

User-agent: *

# Block private/authenticated paths
Disallow: /dashboard
Disallow: /api/
Disallow: /admin/
Disallow: /auth/
Disallow: /sign-in
Disallow: /sign-up
Disallow: /onboarding
Disallow: /settings
Disallow: /internal/
Disallow: /debug/
Disallow: /_internal/

# AI agents: selectively allow public content, block security internals
User-agent: GPTBot
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /openapi.yaml
Allow: /scanner
Allow: /blog
Disallow: /docs/security/

User-agent: Google-Extended
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /openapi.yaml
Disallow: /docs/security/

User-agent: CCBot
Allow: /llms.txt
Allow: /llms-full.txt
Disallow: /docs/security/

User-agent: ClaudeBot
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /openapi.yaml
Allow: /scanner
Allow: /blog
Disallow: /docs/security/

User-agent: PerplexityBot
Allow: /llms.txt
Allow: /llms-full.txt
Disallow: /docs/security/

User-agent: Firecrawl
Allow: /llms.txt
Allow: /llms-full.txt
Disallow: /docs/security/

User-agent: Applebot-Extended
Allow: /llms.txt
Allow: /llms-full.txt
Disallow: /docs/security/

# Keep scraper bots fully blocked
User-agent: Bytespider
Disallow: /

User-agent: FacebookBot
Disallow: /

# Allow Search AI (SearchGPT) to drive traffic
User-agent: OAI-SearchBot
Allow: /

# Sitemap for search engine autodiscovery
Sitemap: https://www.blackveilsecurity.com/sitemap.xml