Home > Lifestyle

6 Smart Ways to Use ChatGPT to Stay Safe Online

By Karrar Haider
A robot holding hand in front with ChatGPT icon on its chest

AI chatbots are useful for gathering information and helping with your research, but do you know that you can use it to stay safe online too? You can avoid many online attacks by using ChatGPT to get a second opinion when you are suspicious. Below are some smart ways you can utilize ChatGPT to stay safe online.

1. Scan Phishing Emails

While phishing emails are often easy to detect, many sophisticated ones can still be very convincing. ChatGPT can scan those emails to look for clues to guess if it’s legit or a scam. You can either provide a screenshot of the full email (hide sensitive info) or open the raw source message and copy/paste its content. For example, to open the raw source in Gmail, click the three dots menu on the right side and select Show original.

Email menu in Gmail

ChatGPT will not only look for clues in the email body, but also the header to confirm it’s from the intended source. Afterward, it will provide complete details about why it thinks it’s a scam or if it’s safe. You can also do this to detect phishing websites or even phishing SMS.

ChatGPT scanning phishing email

2. Scan Commands and Code for Malicious Instructions

You often find commands and scripts online to run on your PC for specific tasks. While most are safe, many can hide malicious instructions to take over your device, like the recent FileFix attack. If you don’t know what each instruction in a command or script does, paste it in ChatGPT to confirm. You can just ask it to check if the code does anything suspicious.

ChatGPT analysing powershell command safety

ChatGPT will break down each instruction so you are sure it doesn’t include any bad instructions. This can work for the source code of open source apps as well. Just copy/paste the code and ask ChatGPT if the code matches the exact purpose of the app.

3. Evaluate Apps and Extensions Permissions

Malicious apps and extensions often ask for permission they don’t need for their function. When you are skeptical about the permissions an app is asking, you can ask ChatGPT to confirm if it actually needs the specific permission. You can usually find all the permissions on the app/extension listing page or when downloading it.

ChatGPT reviewing app permissions

You can screenshot or copy/paste the permissions of an app in ChatGPT and tell the app’s purpose. It will tell you why it needs specific permissions to work. While you can provide the app/extension link directly, we don’t recommend that, as ChatGPT often fails to retrieve full permissions just from the link. However, a direct link can help it search for more information about it.

4. Scan Privacy Policies and Terms of Service

Many shady companies have privacy-invasive policies or company-favoring terms that users normally won’t accept. However, they hide them in lengthy pages with lots of legal jargon, so an average user doesn’t see them. ChatGPT can instantly summarize lengthy privacy policies and TOS pages and separate concerning points.

ChatGPT analysing Grammarly Terms

If you have a specific concern, you can directly ask if the page has anything related to it. Otherwise, just ask it to tell if there are any privacy-invasive policies or terms that could negatively impact users.

5. See How Much of Your Information is Revealed Online

If you’re concerned about how much information is publicly available about you, or worse, you think you got doxed, ChatGPT can help. ChatGPT can run a deep search based on the basic information you provide to identify yourself, to see how much information is available about you online.

The precision will depend on the information you are willing to share, like name, work, email, city/country, etc. You can use a simple prompt like “Search the web for profiles, bylines, images, posts, forums, public records, and news about me. Use the information below to identify me: (provide information)”.

It may not be able to find hard-to-access information, like data-broker websites or data breaches, but you’ll get a general idea of information someone else can find about you, and if any sensitive information is publicly available.

6. Detect Scamming Tactics

Scammers can employ many tactics for attacks, like calling scams, pig butchering scams, or even AI scams. If you are suspicious about an interaction (especially unsolicited ones), you can share details with ChatGPT to get a second opinion. Either tell it what happened, or share the conversation if it’s via messages.

ChatGPT can detect most of the known scam tactics and tell you exactly what the scammer wants to do. Even if it’s a new tactic, ChatGPT can still point out red flags to keep you safe.

While ChatGPT is handy to confirm suspicions, it can still make mistakes. So make sure you double-check the information it provides and make a sound decision. You can also use these prompt generator tools and hacks to get better results from ChatGPT.

Subscribe to our newsletter!

Our latest tutorials delivered straight to your inbox

Karrar Haider Avatar
Karrar Haider
Karrar is always exploring new tech opportunities and finding ways to improve consumer tech. He has a habit of calling technology “Killer”, and is unapologetically dedicated to his PC. When he is not writing about technology, you’ll find him grinding for the best gear in his favorite MMO.

Read next

When Cingular chief Stan Sigman backed the original iPhone before its 2007 unveiling, he accepted terms American carriers usually refused: no logo on the device, no control over its software, no preloaded apps, and a share of monthly subscriber revenue flowing back to Apple, after signing on without seeing a prototype
In 2016, archaeologists dated two rings of snapped stalagmites in France’s Bruniquel Cave to 176,500 years ago, evidence that Neanderthals had walked 336 metres into darkness with fire and built architecture deep underground long before modern humans reached Europe
Otto von Bismarck was 74 when Germany adopted the world’s first national old-age social insurance program in 1889, setting the pension age at 70 after years of fighting socialists with bans, laws, and a promise few workers would live long enough to use
When cosmonaut Valeri Polyakov stepped out of his Soyuz capsule in March 1995 after 437 consecutive days aboard Mir, doctors recorded him at several centimetres above his pre-flight height, and his spine had become so unaccustomed to gravity that the recovery team carried him to a chair rather than risk the compression of letting him walk.
A contemplative scene with two scientists in a vintage laboratory setting.
When Harvard astronomer Cecilia Payne submitted her 1925 doctoral thesis arguing that the Sun was made almost entirely of hydrogen, the field’s senior figure Henry Norris Russell talked her into adding a line calling the result ‘almost certainly not real,’ and then published the same conclusion himself four years later to widespread acclaim.
When Edme Mariotte stared at marks on a wall in the 1660s, one mark vanished inside a six-degree hole where the optic nerve leaves the eye and the brain has been filling in wallpaper, sky, and faces ever since
When seismic waves from the Chicxulub impact reached what is now North Dakota roughly ten minutes after the asteroid struck, they appear to have triggered a ten-metre standing wave in an inland river that flung fish onto the bank and buried them under glass beads still falling from the sky.
When survivors near Lake Nyos woke on the morning of 22 August 1986, the cattle were dead in the fields, the birds had fallen out of the trees, and 1,746 of their neighbours were lying where they had stood the night before, with no fire, no flood, and no wound to explain it.