Question 1

What is Wardnox?

Accepted Answer

Wardnox is a configurable Discord security and anti-scam platform. It resolves messages past the disguises attackers use, weighs evidence from twenty independent detectors across four stages, and applies only the response an administrator configured, with a readable explanation behind every decision.

Question 2

Does Wardnox come with a scam blocklist?

Accepted Answer

No, and that is deliberate. It ships with no hardcoded scam phrases that block anything on their own. What it catches is either a rule you wrote or a combination of weak signals it can account for to you. The example rules are clearly labelled as examples so nobody mistakes them for a curated ruleset.

Question 3

Will it start deleting messages as soon as I add it?

Accepted Answer

No. It starts in monitor mode, which scans, scores and logs everything while enforcing nothing. You read a day of real decisions against your own traffic before switching enforcement on deliberately. The bot also says nothing in your server when it joins.

Question 4

How does it handle disguised scams?

Accepted Answer

A filter that only reads what was typed loses to anyone willing to type it differently. Wardnox resolves each message past the common families of disguise before any rule looks at it, covering look-alike characters, invisible ones, text broken apart, and content wrapped in other content. Your moderators are told which form of a message a rule matched, so a catch is never unexplained.

Question 5

Can a bad rule of mine take down my server?

Accepted Answer

No. Patterns are checked for dangerous constructions before they can be saved, and run isolated and time bounded so a bad one cannot stall anything. A rule that starts misfiring at scale is pulled automatically and your moderators are notified, before it becomes a mass deletion.

Question 6

What data does Wardnox store?

Accepted Answer

Clean messages are never stored. The overwhelming majority of traffic is examined in memory and written nowhere. It never stores direct messages, voice, presence, typing, Discord access tokens at rest, or the contents of attachments. Turning message content storage off entirely is fully supported and does not affect how well it detects anything.

Question 7

What is sent to anybody else?

Accepted Answer

Nothing, until you switch something on. Link resolution, threat intelligence and AI review are each off until an administrator enables them, and being on a paid plan does not switch any of them on: a plan decides what you may enable, never what runs. Threat intelligence is available on Pro and Scale only. When enabled, what is sent is limited to what is needed to ask the question, and never user IDs, usernames, channel IDs or guild IDs.

Question 8

Do I have to host anything?

Accepted Answer

No. We run it. You invite the bot to your server, configure it from the dashboard, and there is nothing to install, update or keep online. Wardnox is a hosted service and the source is not distributed.

Question 9

What does it cost?

Accepted Answer

There is a free plan with no time limit and no cap on how many messages are scanned, then Guard at $9 a month, Pro at $29 and Scale at $99. Every server starts on a fourteen day trial of Pro, with no card. What the paid plans sell is the AI: conversation, a knowledge base built from your own documentation, and higher ceilings. Protection itself is free on every plan.

Question 10

What is Guard, and why would I not just want Pro?

Accepted Answer

Guard is the whole security engine with no chatbot attached. Most people who install a security bot do not want a conversational one, and Guard is for them: the daily cap comes off the AI scam checker, you get more rules and a month of history, and nothing else changes. It is not a trial of Pro or a lesser version of it. A large server can sit on Guard permanently and be getting exactly what it wants.

Question 11

If I stop paying, does my server become less safe?

Accepted Answer

No. Every detector that is ordinary computation keeps running, all of your rules stay exactly as you wrote them, and enforcement continues untouched. What you lose is the AI: conversation, the knowledge base, threat intelligence, and the uncapped scam checker. A downgrade limits what you can add next; it never switches off something already protecting you.

Question 12

Do you charge per member?

Accepted Answer

No. A quiet server with thirteen thousand members costs us almost nothing to run, and a busy small one with a chatty bot costs real money. Credits already price activity directly, so charging for size as well would be charging twice for the same thing.

Question 13

What is a credit?

Accepted Answer

One thing the AI does for you: answering a member, checking a borderline message, or reading a document into the knowledge base. Roughly one reply to one credit, and a scam check costs about half that. Everything the AI does spends credits and nothing else does, so scanning, blocking, enforcing, verification, welcome messages and logging are never metered, on any plan, at any volume. Your monthly allowance refills and does not stack up; credits you have bought stay until you spend them.

Question 14

What happens when the trial ends?

Accepted Answer

The server moves to Free and keeps every rule and setting you made. Detection and enforcement carry on untouched. What stops is the conversation and the knowledge base, and the AI scam checker goes back to a daily cap. Trial credits you had not spent are removed at that point, because they belong to the trial rather than to the account. Credits you bought are yours and are not touched.

Documentation

Getting started

Not here yet