I Tried Malwarebytes' ChatGPT App, and It's Actually Good at Detecting Scams

A few months ago, ChatGPT got an app store of its own, which means you can access tools like Photoshop and Apple Music right inside the ChatGPT prompt box. Now Malwarebytes has joined the ChatGPT app store, which means you can get some expert help when investigating web links, emails, text messages, domains, and phone numbers you think might be suspicious.

The app is free to use for everyone, whether or not they're signed up to a paid ChatGPT subscription, and you can enable the tool via the ChatGPT app store or by entering the prompt "Malwarebytes, is this a scam?" Once you've used the app for the first time, you can access it again via the + (plus) button on the prompt box.

Malwarebytes' ChatGPT app can test links, sites, and phone numbers

Malwarebytes will do a deep security dive into links you provide. Credit: Lifehacker

You can paste just about anything you like into a conversation with the Malwarebytes plugin, but there are certain approaches that scammers will often take—including links contained in phishing emails—that make for good candidates to test this thing out. I dived deep into my email spam folder to find some URLs to test Malwarebytes on, and gave it a few trustworthy web addresses as well—you just copy the link into the prompt box and ask the app for an assessment.

Malwarebytes successfully sifted out the scam links from the safe ones, even when it didn't have any specific information in its databases about the links I was providing. When it was unsure, it said so, with lots of extra context: For example, for one URL I was told the address was "a legitimate email security and tracking service used by companies to rewrite links" but one that scammers also used to conceal the link destination.

You also get an assessment of the domain name: When given a link to a Lifehacker article, the plugin correctly identified that it was a legitimate domain with a registered owner, even though it didn't have any specific information about the URL. Malwarebytes was also able to spot domain redirecting, a trick frequently used by scammers.

Phone numbers can be given to Malwarebytes as well: When I tested this out with a few scam calls I've had, these numbers were correctly identified as coming from scammers or at least being suspicious. I like the way the app gives you some context to its thinking (explaining how spam call centers work, for example), and will also offer up advice about next steps and how to stay safe.

Something else I appreciated was that the Malwarebytes app has a memory inside ChatGPT: If you post a series of links and numbers in the same chat thread, as I did, then it will try and put them all in context (explaining why one URL is potentially more dangerous than another, for example).

The Malwarebytes ChatGPT app can also look at messages and emails

You'll get a list back of red flags in email and text message content. Credit: Lifehacker

You can also give the Malwarebytes app some text you've come across in an email or text message and get a verdict on this too—you can even type in a transcript of a conversation you're having on the phone, if you want. The plugin will scan the text for phrasing that scammers often use and will alert you of any other red flags.

I tried this out with a variety of spammy text, and again Malwarebytes scored highly in terms of recognizing anything dodgy. As before, if it came across something it wasn't sure about, it would explain the reasons why and suggest some next steps.

The responses also include some detail on why different scam approaches are taken and why they sometimes work, and how they might escalate—so if you get a message purporting to be from a family member asking for help, Malwarebytes tells you why these scams are common and how they're used to steal identities or money.

It's an intelligent system, in that it'll ask you questions about the texts or emails you've received: If it's not sure about something, you'll be told about extra checks you can run (like looking at the "reply to" address on an email). However, the usual ChatGPT sycophancy does start to grate a bit, as you're constantly told that you're doing the right thing and that you're right to be suspicious.

The app taps into Malwarebytes Threat Intelligence, so it should be able to keep you protected against the latest threats (making it more helpful than a Google search or just a regular ChatGPT query). From the examples I used at least, it comes across as a security tool that's accurate, comprehensive, and easy to use—one that's well worth keeping close at hand if you come across potential scams you're not sure about.

Disclosure: Ziff Davis, Mashable’s parent company, in April 2025 filed a lawsuit against OpenAI, alleging it infringed Ziff Davis copyrights in training and operating its AI systems.

View the full article