← ClaudeAtlas

whisper-brand-protectionlisted

WhisperGraph brand-protection and takedown playbook — find registered lookalike domains impersonating a brand, work out which ones are actually dangerous, attribute them to a registrant, and assemble evidence a registrar or hosting provider will act on. Use when the user asks about typosquats, lookalike or copycat domains, homoglyph or punycode domains, bitsquatting, domain impersonation, phishing domains targeting their company, brand or domain monitoring, a watchlist of domains an attacker might register, or preparing a takedown, abuse report or evidence package. Separates registered from weaponised so a defensive registration is never reported as an attack, and tells the user what the sweep did not cover. Requires the WhisperGraph MCP connector.
whisper-sec/whisper-skills · ★ 1 · AI & Automation · score 63
Install: claude install-skill whisper-sec/whisper-skills
# Brand protection and takedown Three different questions, routinely collapsed into one and answered wrongly as a result: 1. **What lookalikes exist?** — generation, and existence is not a finding. 2. **Which are weaponised?** — threat data, and this is the only one that supports the word "attack". 3. **Who is behind them?** — attribution, which is what makes a takedown stick. Answer them in that order and keep them visibly separate in the output. ## 1. Get the input right You need the brand's **registrable apex** — no scheme, no `www.`, no path. Ask if the user gave you a company name rather than a domain; guessing the apex is how a sweep ends up scanning the wrong thing. Ask which they want before running anything, because they are different jobs: - **Registered lookalikes** — what exists now. This is the actionable sweep and the default. - **A watchlist** — the generated set including names nobody has registered. Useful for defensive registration and for alerting if one appears. Not findings, and must never be reported as such. If the brand owns several apexes, sweep each one. A sweep of the main domain says nothing about the regional ones. ## 2. Run the sweep `run_workflow` with the `typosquat` slug is the whole of step one and most of step two: it generates lookalikes across misspellings and risky extensions, checks which are registered, works out which are the brand's own, and flags the ones that are freshly registered, hidden behind privacy, or already list