47skin.com — AI Site Grade

Analysis

47skin.com is entirely invisible to every AI crawler — and to the open web

Every AI crawler — GPTBot, ClaudeBot, PerplexityBot, Google-Extended, OAI-SearchBot, Applebot-Extended, Bytespider, and all others — receives a 403 with a Cloudflare JS challenge wall when attempting to access 47skin.com. The homepage, robots.txt, llms.txt, and sitemap.xml all return the same Cloudflare challenge page ("Your connection needs to be verified before you can proceed"). No bot can read a single word of site content without executing JavaScript and passing a browser-like challenge, which no AI crawler does.

Crawler Access

The compare_bot_access test across 11 user-agents (including a plain browser baseline) returned 403 blocked for every single one. The site runs on Shopify (IP 23.227.38.32, Google-hosted MX, Klaviyo verification TXT records) behind Cloudflare with managed challenge mode. There is no robots.txt reachable — it returns the same Cloudflare wall. There is no llms.txt — it also 404s into the Cloudflare wall. The sitemap.xml is equally inaccessible. The site has effectively zero machine-readable entry points for AI systems.

Cold-Knowledge Gap

A frontier LLM queried cold about "47skin" returned: "I do not have specific, verifiable information about a company or brand called '47skin.'" The model could not confirm what the brand does, who it serves, or any notable products. This is a complete knowledge vacuum — despite the site describing itself as a multi-award-winning brand with 500,000+ customers, stocked in Harrods and Boots, featured in Vogue, Tatler, and GQ, and ranked in the Sunday Times 100. The gap between the brand's claimed prominence and what AI models know cold is total.

Content & Schema Posture

The live site is a JS shell behind Cloudflare. The Wayback Machine snapshot (February 2026) reveals a full Shopify store: the brand sells anti-blemish and scar-repair skincare built around a patented ingredient called Silver Chitoderm (47 is the atomic number of silver). The homepage carries Organization, WebSite, and BreadcrumbList schema — but no Product schema on the homepage for any of the products displayed. The Silver Chitoderm page does include a well-structured FAQPage schema with 9 questions and answers. The site has answer-format signals (FAQ, tables, lists) but no comparison schema and no Product schema on collection or bundle pages.

External Signals

Despite the brand claiming 10,000+ 5-star reviews, features in Vogue/Tatler/GQ, a Cosmopolitan Beauty Award, and a Sunday Times 100 ranking, web searches returned zero indexed results for the brand name, its products, its Trustpilot page, or any press mentions. The site is either too new to have accumulated external citations, or its content is so thoroughly walled behind Cloudflare that search engines have not indexed it. The DNS TXT records confirm Klaviyo (email marketing) and Google Search Console verification, indicating the brand does attempt SEO — but the Cloudflare challenge is blocking all of it.

Findings

1. Cloudflare JS challenge wall blocks all AI crawlers and search engines High

   Every AI crawler (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, etc.) receives a 403 with a Cloudflare JS challenge wall when accessing 47skin.com. The homepage, robots.txt, llms.txt, and sitemap.xml all return the same challenge page, preventing any bot from reading site content.

   What to change: Configure Cloudflare to allow AI crawler user-agents (e.g., GPTBot, ClaudeBot) through the challenge wall, or serve a static version of the site to bots without JS challenges.

2. Robots.txt is inaccessible behind Cloudflare wall High

   The robots.txt file returns a 403 Cloudflare challenge page instead of crawl directives, meaning no bot can learn which paths are allowed or disallowed.

   What to change: Ensure robots.txt is served without a JS challenge so crawlers can read it.

3. No llms.txt file available for AI crawlers Medium

   The llms.txt endpoint returns a 404 (behind Cloudflare wall), providing no structured guidance for AI crawlers about which content to index.

   What to change: Create an llms.txt file listing key pages and content for AI crawlers.

4. Sitemap.xml is inaccessible behind Cloudflare wall High

   The sitemap.xml returns a 403 Cloudflare challenge, preventing search engines and AI crawlers from discovering the site's pages.

   What to change: Serve sitemap.xml without a JS challenge so crawlers can discover all pages.

5. Cold knowledge gap: LLM cannot identify the brand High

   A frontier LLM queried cold about '47skin' returned no verifiable information, unable to confirm the brand's products, audience, or claims despite the site describing itself as a multi-award-winning brand with 500,000+ customers and press features.

   What to change: Allow AI crawlers to index the site and publish structured data (Product, FAQ, Organization schema) to improve AI knowledge.

6. Homepage lacks Product schema for displayed products Medium

   The homepage includes Organization, WebSite, and BreadcrumbList schema but no Product schema for any of the products shown, missing an opportunity for rich AI understanding.

   What to change: Add Product schema markup to each product displayed on the homepage.

7. No comparison schema on product or bundle pages Medium

   The site lacks comparison schema (e.g., ProductGroup or individual Product comparisons) on collection or bundle pages, reducing AI's ability to present product comparisons in search results.

   What to change: Add comparison schema (e.g., ProductGroup) to collection and bundle pages.

8. Zero indexed web presence despite claimed prominence High

   Web searches for the brand name, products, Trustpilot page, and press mentions returned zero results, indicating the site is either too new or completely blocked from search engine indexing.

   What to change: Remove the Cloudflare JS challenge for search engine bots and AI crawlers to allow indexing.

9. No external backlinks or press mentions found Medium

   Despite claims of features in Vogue, Tatler, GQ, and a Sunday Times 100 ranking, no external citations or backlinks were found in web searches, suggesting either the claims are unsubstantiated or the site is too new.

   What to change: Build backlinks through PR and partnerships, and ensure press mentions link back to the site.

What's working

• FAQPage schema on Silver Chitoderm product page — The Silver Chitoderm page includes a well-structured FAQPage schema with 9 questions and answers, providing rich answer-format signals for AI.
• Organization and WebSite schema on homepage — The homepage includes Organization and WebSite schema markup, establishing basic brand identity for AI crawlers.
• Google Search Console verification in DNS TXT records — DNS TXT records include Google Search Console verification, indicating the brand has attempted SEO setup.
• Klaviyo email marketing integration confirmed — DNS TXT records include Klaviyo verification, showing the brand uses email marketing tools.