More in Refunds, Complaints & Scams.
Check suspicious texts and emails for scams with Norton in ChatGPT
Copy the prompt below and paste it into the AI tool named on this page.
Prompt Improved prompt
Our fuller version of the source's prompt, or one written to avoid a problem in the source. Not tested by the poster. It doesn't change what happened in the source.
Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish. Goal: Check whether a message I received is a scam before I respond or click anything. Questions to ask me first: - Where did the message come from (text, email, social media), and who does it claim to be? - Do you have an account with that company? - Have you clicked a link or shared any information yet? Inputs (fill in or confirm): - Screenshot or pasted text of the message, without clicking links: [MESSAGE] - The sender's address or number: [SENDER] - What it asks me to do: [REQUEST] Rules: - Give a verdict (likely scam, likely real or can't tell) with the specific warning signs you see. - If you can't tell, say so and list what would settle it. - Tell me how to check directly with the company using a phone number or site I find myself. - If I already clicked or shared something, list the steps to protect my accounts now. Checkpoint: Give me the verdict and red flags first, before any longer explanation. If you get stuck: If the screenshot is unclear or missing the sender, ask me for it. Verify before you finish: Check that the advice never asks me to use a link or number from the suspicious message. Output: A short verdict, the red flags and the safe next step. Done when: I know whether to delete, report or verify the message through the real company.
Customize this prompt
Answer these questions and we'll put your answers into the prompt for you. You can leave any of them empty.
Your file stays on your device. Nothing is uploaded to TriedPrompts.
Your prompt
Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish. Goal: Check whether a message I received is a scam before I respond or click anything. Questions to ask me first: - Where did the message come from (text, email, social media), and who does it claim to be? - Do you have an account with that company? - Have you clicked a link or shared any information yet? Inputs (fill in or confirm): - Screenshot or pasted text of the message, without clicking links: [MESSAGE] - The sender's address or number: [SENDER] - What it asks me to do: [REQUEST] Rules: - Give a verdict (likely scam, likely real or can't tell) with the specific warning signs you see. - If you can't tell, say so and list what would settle it. - Tell me how to check directly with the company using a phone number or site I find myself. - If I already clicked or shared something, list the steps to protect my accounts now. Checkpoint: Give me the verdict and red flags first, before any longer explanation. If you get stuck: If the screenshot is unclear or missing the sender, ask me for it. Verify before you finish: Check that the advice never asks me to use a link or number from the suspicious message. Output: A short verdict, the red flags and the safe next step. Done when: I know whether to delete, report or verify the message through the real company.
Scroll to see the whole prompt. Your answers show in green.
3 blanks are still empty: Screenshot or pasted text of the message, without clicking links; The sender's address or number; What it asks me to do. They'll stay in brackets in your prompt, so the chat tool may ask you about them.
What you type stays in this browser tab. We don't send it or save it, and it's gone when you leave the page. If you use a "Try this in" button, your answers go to that tool as part of the prompt.
Try this in:
This prompt has blanks to fill in, like [MESSAGE]. We'll copy it instead of filling it in, so you can edit it before you send.
Opens in a new tab. We don't see what you send.
These links are only a shortcut. We're not affiliated with OpenAI, Google or xAI, and your results may not match the source.
The prompt they actually used (our rebuild)
The source didn't share its exact prompt, so we wrote this from what it describes.
Uploaded a screenshot of the suspicious message to ChatGPT with the Norton app enabled.
AI tool
Outcome
Tom's Guide writer Amanda Caswell added the Norton scam-detection app inside ChatGPT and tested it on real messages by uploading screenshots. The first test, a text about a part-time job, came back 'Unknown,' with only general advice to be careful with unsolicited job offers. A real email claiming a payment had been declined, which looked believable because Caswell had just updated a credit card, was flagged within seconds with 'high confidence' as phishing aimed at payment details. A vague money-making email from someone named Mark was flagged with high confidence as a 'gambling scam,' and a real Lollapalooza lineup email that had landed in spam was judged legitimate, with a note to stay cautious.
Evidence: Article or interviewA newsletter, journalist or interview account of what happened.
Known limitations
PartialThe source says it only partly worked, or had a significant problem a person had to deal with.
What went wrong: It caught the phishing and gambling emails, but couldn't judge the first screenshot, a job-offer text.
Source
- Posted
- by Amanda Caswell (Tom's Guide)
- Last checked
- Method:
- How we verify
Context: The article includes affiliate promotion for Norton products. Only a handful of messages were tested, and Norton itself says it won't catch every scam.
More in Refunds, Complaints & Scams
Win a security deposit small claims case against a landlord with ChatGPT
After Chris Maloney, 23, and partner Nadia Syed, 22, moved out of their apartment in Amherst, New York, their landlord kept about $1,000 of the deposit for cleaning and repair costs. Maloney ran the lease through ChatGPT, which found that New York caps security deposits at one month's rent, while the couple had paid a month and a half. With no lawyer, Maloney used ChatGPT to build the case and took the landlord to court. Both sides presented before a judge on Oct 17, and the judgment came back in Maloney's favor, awarding $1,180.
PersonalRefunds & scamsChatGPTWorkedRecreated promptEvidence: Article or interviewBeginner-friendlyView CaseCheck a pre-IPO investment offer after a refused payout with ChatGPT
A 77-year-old retiree in Bengaluru, India, was approached by people posing as representatives of IIFL Wealth Management who promised 'pre-IPO allotments in sizable quantities.' Over several weeks the retiree paid in money for share allotments that showed large paper profits. When a request to release ₹40 lakh was refused, the retiree grew alarmed and started investigating the company's background in ChatGPT, according to the police report. The search showed it was a fraudulent organization with a lot of complaints against it. By then ₹67.10 lakh was already lost, but the check stopped further payments, and a police report was filed on January 3 with the Cyber Crime Police Station under IT Act Sections 66C and 66D.
PersonalRefunds & scamsChatGPTPartialRecreated promptEvidence: Article or interviewView CaseSpot a jury duty scam targeting your spouse with ChatGPT (partial)
On July 21, men posing as sheriff's deputies told Kimberly Fudge, 38, a Florida finance manager, that Fudge had missed federal jury duty and faced arrest. Fudge spent nearly 10 hours driving and feeding $25,000 into cryptocurrency machines as 'bail'. Following the callers' script, Fudge texted spouse Jonathan for money, and Jonathan sent $3,000. At a second request, Jonathan asked ChatGPT why a spouse would make such a demand. It listed ordinary explanations, then flagged a possible scam, and Jonathan called 911. The money already sent is gone; reports went to the sheriff's offices, the FBI's Internet Crime Complaint Center and the FTC, but the family is 'not counting on recovery.'
PersonalRefunds & scamsChatGPTPartialRecreated promptEvidence: Article or interviewView CaseAsk ChatGPT whether an online crypto 'investment' is a scam
Margaret Loke, a 70-something widow in San Jose, met a man called 'Ed' on Facebook who persuaded Loke to 'invest' in crypto through an app that showed big profits. Loke wired money from an IRA, including $120,000 and a final $62,000, and took out a $300,000 second mortgage. When the account was 'frozen' and Ed demanded a million dollars to unfreeze it, Loke asked ChatGPT, which replied: 'no, this is a scam, you better go to police station'. That warning came too late: Loke lost nearly $1 million in a 'pig butchering' scheme, faces a huge tax bill for withdrawing the IRA at once, and could lose the house.
PersonalRefunds & scamsChatGPTWorkedRecreated promptEvidence: Article or interviewView CaseFind a mystery Microsoft charge, cancel it and get a full refund with Muse
Diego found a mystery $83 Microsoft charge on a checking account and asked Muse to look into it. In about two minutes it identified Drawboard PDF Plus at $83.49 a year, renewing each September, and found the same charge from the year before. Muse turned off recurring billing in Diego's Microsoft account; with no self-serve refund for third-party subscriptions, it opened a live chat with Microsoft Support, where Diego had to type a 6-digit verification code. A full $83.49 refund to PayPal within 30 days was approved. Muse then audited the account and found an unused Microsoft 365 Family subscription at $129.99 a year, whose renewal Diego had it cancel.
PersonalRefunds & scamsMuseWorkedRecreated promptEvidence: Described by posterView CaseGet a parking garage refund over the phone with Muse after the valet turned the car away
Kyle G paid for parking in San Francisco, but the valet refused the car because Kyle only had a phone key. After the meeting, Kyle asked Muse to handle the refund. Its first call failed because customer support needed more details; Muse came back, asked Kyle a couple of questions and called again. On the second call a full refund was approved.
PersonalRefunds & scamsMuseWorkedRecreated promptEvidence: Described by posterView Case
Related cases
Plan a week of meals for a family of four under $300 with ChatGPT
To test whether AI can trim a grocery bill, a WDIV Local 4 newsroom team in Detroit asked ChatGPT to create a weekly meal plan and grocery list for a Detroit-area family of four with two children, targeting around $300. When the team priced the list at Kroger online, including store savings and coupons, the total came to approximately $250. The station noted that it did not check whether the groceries would actually provide enough food for a family of four for a full week.
PersonalMeals & cookingChatGPTWorkedRecreated promptEvidence: Article or interviewBeginner-friendlyView CaseShortlist used Volvos and prep dealer questions with ChatGPT
Sara Clarke, replacing a car bought in 2010, used ChatGPT to search dealerships within a few hours of the Washington, DC, area for Volvo XC60 and V60 models, narrowing by year, mileage, trim, features and color. Its results were similar to Clarke's own searches, though it occasionally surfaced cars that were older or more expensive than requested. It then drafted questions for dealers, such as asking for the CPO inspection checklist and a Carfax or AutoCheck report, whether dealer add-ons were required and the out-the-door price with all taxes and fees. Clarke used those alongside consumer guides to collect quotes by email, phone and text. Its financing-office advice was useful, but it kept recommending steps Clarke had already done, such as asking for all-in pricing. Clarke said it didn't guarantee a better price but kept the process organized and less stressful.
PersonalCarsChatGPTWorkedRecreated promptEvidence: Article or interviewBeginner-friendlyView CaseBuild a custom ChatGPT reading tutor for a dyslexic child
Arlyn Gajilan's 11-year-old son, Tobey, who is dyslexic, came home saying, 'Everyone keeps telling me I'm smart, but I'm just so slow.' Gajilan built a custom GPT in ChatGPT to help Tobey with reading fluency, spelling and organizing written work. Gajilan fed it Tobey's report cards, neuropsych evaluation, hobbies and competitive streak so lessons were gamified, set it up to encourage progress even when Tobey struggled, and after each session asked it, 'Why this choice?' or 'What is he learning?' Within weeks, Tobey was gaining confidence. Gajilan later turned the idea into a paid tutoring platform, while saying human tutoring is 'absolutely 100% the gold standard.'
PersonalKids & schoolChatGPTWorkedRecreated promptEvidence: Article or interviewBeginner-friendlyView Case