Patch Notes — June 22

Improved False Positive Handling

We’ve upgraded how AntiScamBot handles false-positive reports from server staff.

When staff click False Positive on a moderation alert, the bot now treats that report as a server-specific correction instead of changing detection globally.

What changed

• False-positive image reports now apply to your server only.
• If your staff mark an image detection as a false positive, AntiScamBot will avoid acting on that same image again in your server.
• This prevents one server from weakening protection for everyone else.
• If multiple independent servers report the same detection as a false positive, it will be sent to bot staff for manual review.
• Global detection behavior will not be changed automatically.

Abuse protection

To keep the bot safe:

• Only server staff can review moderation alerts.
• False-positive reports are counted by unique servers, not repeated clicks.
• One server cannot disable detections globally.
• Bot staff must review repeated cross-server false-positive reports before any global changes are made.

Why this matters

This makes AntiScamBot better at adapting to each community while keeping scam protection strong across all servers.

Your server gets more control over mistakes, but malicious servers cannot abuse the system to make scams harder to detect globally.

Patch Notes — June 22

Big update this week. We’ve been heads-down on a rewrite of the backend for a while now, and it’s finally in. Here’s what changed.

Core bot rewritten in Rust
The old Python bot has been fully replaced with a Rust implementation. It’s faster, handles errors more reliably, and uses less memory. We also removed a bunch of legacy code that wasn’t relevant anymore.

User-facing
- DMs now always go out when the bot removes a scam message. Previously this was behind a setting most servers didn’t enable, so a lot of users never got any explanation. The DM now also includes a link to this server so they can appeal if they think it was a mistake.

Moderator tools
- Image previews in alerts: fixed a bug where scam image previews would break in mod alerts if the original message was deleted. The bot now uploads the preview directly into the alert embed, so you can always see what was caught.
- Feedback buttons: added Confirmed Scam / False Positive buttons directly on mod alerts. Staff can review detections in one click.
- Feedback polls: new servers with 30+ members get a one-time staff satisfaction poll so we can improve based on what you actually need.
- Evidence export: prepared a scam evidence export command for mods (available on request if useful for your server).

Infrastructure
- Updated the NuExtract image-scanner server to be safer under load: body-size limits, IP allowlist, and more predictable GPU scheduling on the A4000.
- Updated systemd configuration for better autorestart behavior on the host.

Housekeeping
- Removed all old Python files, cached data, and the old web dashboard stuff. The repo is much cleaner now.

If anything feels off after this rollout, post in bot-issues and we’ll take a look.

Patch Notes – AntiScamBot Update (2026-06-03)

What’s new:

• Longer watch for new members: The bot now monitors members for 24 hours after they join (up from 30 minutes), checking their messages throughout that period for scam patterns.
• Smarter scam detection for recent joins: Updated the model to look for specific scams like:
• Fake business offers (“inbox me for paid reputation/review removal”).
• Out-of-context funds/sales/profit screenshots used as proof of earnings.
• Broad creative/marketing bios (only flagged unless paired with stronger evidence like links or payment requests).
• Timeouts no longer trigger global watching: Being timed out in Discord (for any reason) will no longer cause the bot to watch that user globally for future messages.
• Cross‑guild checks are scam‑focused: When the bot sees a user who was moderated in another server, it only counts that as a risk if the prior action was scam‑related (not just a timeout or unrelated moderation).
• Faster image handling: The bot can now reprocess multiple images at the same time (using a thread pool), so it stays responsive while scanning pictures.

Patch Notes – AntiScamBot (2026-05-29)
New Join‑Account Scam Detection
- Checks newly joined members for scam/fake‑account signals using AI image analysis + profile metadata (username, avatar, bio, banner, badges, account age, etc.).
- Configurable via /setupbot and /antiscam‑settings: Off (default), Flag only, or Flag + Kick.
- When enabled and a suspicious join is detected, the bot posts an alert to the configured moderation channel.
- In Flag + Kick mode, the bot will attempt to kick the user.

Enable the feature in your server with /setupbot or tweak it later via /antiscam‑settings.

AntiScamBOT Update

We’ve improved image scam detection to reduce false positives and catch more dangerous posts.

• Normal in-game screenshots, such as spins, tickets, rewards, inventories, and game UI, should be handled better.
• Posts telling users to turn off Windows Smart App Control, antivirus, Defender, firewall, or other security protections will now be treated as dangerous.
• The bot should be better at telling the difference between harmless game content and scam/malware instructions.

This update helps keep the server safer while reducing unnecessary flags on legitimate screenshots.

AntiScamBot Patch Note

We’ve upgraded how AntiScamBot detects scam images.

The bot now uses a newer image understanding system instead of the previous OCR-based approach. This means AntiScamBot no longer has to rely mainly on pulling text out of an image and matching it against rules. It can now look at the full image context more directly, including things like fake Nitro gifts, suspicious Discord-style screenshots, fake promotions, scam links, and misleading visual layouts.

What changed
- Improved scam image detection.
- Better understanding of fake Discord/Nitro screenshots.
- Fewer missed scams caused by hard-to-read or stylised text.
- Fewer false positives from harmless screenshots.
- No more public “scanning” or benchmark-style messages in chat.
- If a scam image is detected, the bot silently follows the server’s configured actions:
- delete the message if enabled
- timeout the user if enabled
- send moderator alerts if enabled
- report according to server settings

Why this is better
The old system depended heavily on OCR, which meant detection could be affected by blurry text, weird fonts, screenshots, image compression, or partial text. Scam images often try to hide behind exactly those tricks.

The new system is better at judging the image as a whole, not just reading words from it. That makes it more reliable for modern scam posts, especially fake Discord gift screens, Nitro scams, impersonation attempts, phishing pages, and copied giveaway images.

What server owners need to know
Your existing moderation settings still apply. If your server has auto-delete, alerts, timeouts, or reports configured, AntiScamBot will continue using those settings..

Changelog 5/22/2026

Security Improvements
- Added protection against oversized images that could overload the server — oversized images are safely ignored before being processed.
- Added phishing payload detection — suspicious file patterns in images are now blocked.
- Added image dimension limits to prevent memory exhaustion attacks.

Performance Improvements
- The image-scanning system now automatically adjusts how fast it processes images. When scam traffic spikes, it speeds up. When it's quiet, it slows down to save resources. Users shouldn't notice any difference, but server load is much more stable.

AntiScamBot Performance & Stability Update

We've made under-the-hood improvements to keep the bot fast and reliable, even as it grows to protect more servers.

What's better:
- The bot now uses smarter limits on heavy tasks (like scanning images) so it never gets overloaded, even when many servers are active at once.
- New built-in metrics help us spot and fix slowdowns before they affect you.
- Startup and reconnections are smoother, with less strain on Discord's services.
- Image scanning is more efficient, reducing delays when checking pictures for scams.

These changes mean faster responses, fewer hiccups, and better protection as the network grows.

AntiScamBot — Patch Note

/manage-allowed-domains is now live.

Server owners and moderators (assigned via /antiscam-mod-roles) can open an interactive panel from:
- /manage-allowed-domains — direct command
- The Allowed Domains row in /antiscam-settings

Use the panel to:
- Add trusted domains to a whitelist
- Remove domains with a single click
- Toggle "Delete non-allowed URLs" on or off from the embed header

When the toggle is on, any message containing a URL whose host is not in the allowlist is automatically deleted — applies to both new messages and edited messages.

AntiScamBot Language Update

AntiScamBot now supports server and personal language preferences. Server owners can set a default bot language with /server-language, or leave it on auto-detect so the bot uses the server's Discord locale when available.

Members can also choose their own language with /language. Personal language preferences apply to command replies, embeds, settings panels, help text, and direct messages when translations are available.

Supported languages include English, Spanish, French, German, Dutch, Italian, Portuguese, Swedish, Norwegian, Danish, Finnish, Polish, Turkish, Russian, Ukrainian, Japanese, Korean, Chinese, Hindi, and Arabic. Missing text falls back to English.

AntiScamBot Update — Domain Age Detection

New Feature: Newly Registered Domain Detection
Scammers often register fresh domains for phishing campaigns. We now check domain registration dates via RDAP lookups to catch these early.

How it works:
- Extracts domains from URLs shared in messages
- Checks registration date against public RDAP records
- Uses tldextract to identify the registered domain (ignores subdomains)
- Aggressively cached results to minimize lookups

Scoring (age-based):
- 🔴 0–7 days: +5 score
- 🟠 8–14 days: +4 score
- 🟠 15–30 days: +3 score
- 🟡 31–60 days: +2 score
- 🟢 61+ days: +1 score (up to threshold)

Server Configuration:
Each server decides how to handle newly registered domains:
- Enable/disable domain age checks per server
- Action choice: Flag only (alert mods) or Delete + Flag (remove message + alert)
- Custom threshold: Pick from 7, 14, 30, 60, or 90 days
- Configurable via /setupbot command or /antiscam-settings panel

AntiScamBot Update

We’ve improved AntiScamBot’s link protection to better catch known scam domains in messages.

What’s New

• AntiScamBot now checks posted links against our known scam domain list.
• This works for both new messages and edited messages.
• Links can be detected with http://, https://, or no prefix at all.
• If auto-delete is enabled, known scam links can be removed automatically.
• If moderation alerts are enabled, staff will be notified in the configured mod channel.

What This Means

If someone posts or edits in a known scam domain, AntiScamBot can remove it and alert moderators faster.

Normal links are not blocked just because they contain http:// or https://. They only trigger this new protection if the domain is on the scam domain list.

AntiScamBOT Patch

AntiScamBOT now checks scam images sent as links, not just uploaded attachments.

• image links in messages are now downloaded and scanned with OCR.
• Discord CDN/media links are supported, including links like media.discordapp.net and cdn.discordapp.com.
• Common image links such as .jpg, .png, .webp, .gif, and similar formats are supported.
• Scam screenshots hidden behind image URLs can now be detected the same way normal attachments are.
  This means users can no longer bypass image scanning by posting the scam image as a link instead of uploading it directly.

We’re introducing an important update to our bot’s moderation system to keep our space safer for everyone.

What’s changing?
The bot will now automatically flag:

• Child exploitation (CP) content – any attempts to share, reference, or solicit such material will be detected and flagged immediately for review.
• Suspicious links – including known malware, phishing, scam domains, or redirects to harmful sites.
• Other high-risk violations – such as hateful content, severe harassment, or platform policy breaches.

What’s NOT changing?
The bot will fully respect your existing moderation settings. If you have disabled certain alerts, auto-mod actions, or log channels, those preferences remain intact. This new detection layer works within your current configuration (e.g., only log, or log + delete, or just warn).

How will you see flagged items?
Depending on your server’s settings, flagged content will appear in your designated moderation log or alert channel, with a clear reason label. No action will be taken automatically unless you have enabled that option.

Keep in mind, i am still working on it. please DM me links you want to be flagged too.

Hey everyone! We're considering expanding our anti-scam bot to moderate not just scams, but also general text content—like filtering suspicious links and other potentially harmful messages. We'll make everything toggleable, so you can choose what the bot should moderate.

By default, these new features will be turned OFF. and you will need to enable it in order for the bot to start moderating links etc

This would help keep the server even safer. What do you think? Vote yes if you'd like us to implement this, or no if you prefer to keep things as they are(Only image moderation)

Vote yes(1️⃣) or no(2️⃣)

📢 Announcements

The single source of truth for bot updates.
──────────────────────────────

📥 What you’ll see here

🚀 Releases — new features & versions
🔧 Maintenance — planned downtime windows
🚨 Incidents — outages & post-mortems
🎉 Milestones — big wins worth celebrating

🔔 Get notified

Right-click the channel → Notification Settings → All Messages.
Or just follow this channel in your own server (integrations → webhooks).
Read-only • staff announcements