Search

# 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: /

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

User-agent: *
Allow: /

# The sign-in/dashboard subdomain is not for crawlers.
Disallow: /signup?
# Don't waste crawl budget on screenshot exports
Disallow: /Showcase/_screenshots/

Sitemap: https://whitecapdata.com/sitemap.xml

# RFC 9116 — security.txt for whitecapdata.com
# Cross-reference: Security-Compliance-Master-Plan-2026 §B.4 #11
# Source-of-truth: apps/site/.well-known/security.txt in the WhiteCapData monorepo.
# Update Expires before the date below — the file is treated as stale after.

Contact: mailto:security@whitecapdata.com
Contact: mailto:thomas@whitecapdata.com
Expires: 2027-05-26T00:00:00Z
Preferred-Languages: en
Canonical: https://whitecapdata.com/.well-known/security.txt
Policy: https://whitecapdata.com/trust/vulnerability-disclosure-policy

# Acknowledgments: https://whitecapdata.com/trust/researcher-hall-of-fame
# (Hall of fame is published once we receive a first valid report.)