whisper-brand-protectionlisted
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