online scam and risk checker
Evaluates messages and links to identify phishing, scams, and social engineering risks with structured assessments.
$5
Works with the AI tools you already use
online scam and risk checker
Example session with this skill installed
I got an email from 'Netflix Support' at security@netflix-billing-update.com saying my payment failed and I need to update my card in 2 hours or my account gets deleted. Link: bit.ly/net-fix-99
- Read your context and instructions
- Compiled the online scam
I have analyzed the message content and the provided link. This communication exhibits multiple high-confidence indicators of a phishing attempt.
Risk Assessment: Netflix Payment Failure Email
1. Quick Summary
This is a high-risk phishing attempt designed to steal credit card information. It uses a fake domain and extreme urgency to bypass critical thinking.
2. Known Facts (Background Knowledge)
- Netflix typically communicates via the
netflix.comdomain, not third-party billing domains. - Phishing campaigns frequently use URL shorteners (like bit.ly) to hide the final destination of a malicious site.
- Legitimate services generally provide a grace period of several days for payment issues rather than a 2-hour deletion threat.
3. Warning Signs Present
- Fake Domain: The sender address
netflix-billing-update.comis not an official Netflix domain. - Urgency Trigger: The "2 hours or account deleted" threat is a classic social engineering tactic.
- Obfuscated Link: The use of a bit.ly link prevents the user from seeing the actual destination without clicking.
- Mismatched Branding: The URL text "net-fix" is a common misspelling used to bypass spam filters.
4. Unknowns / What Cannot Be Verified
- The actual destination of the bit.ly link.
- Whether your specific Netflix account actually has a billing issue.
5. Practical Risk Assessment
Risk level: HIGH
The combination of a non-official domain and a 2-hour deletion threat is almost exclusively seen in credential and financial theft scams.
6. Plain-Language Concerns
If you click the link, you will likely be taken to a fake website that looks exactly like Netflix. Any credit card details you enter there will be sent directly to scammers, who may then use your card for unauthorized purchases.
7. Independent Verification Steps
- Open a new browser tab and manually type
www.netflix.com. - Log in to your account directly.
- Navigate to "Account" -> "Billing Details" to check your status.
- Check the official Netflix help center for their authorized sender list.
8. Recommended Safer Next Steps
- Do not click the link or reply to the email.
- Mark the email as "Phishing" or "Spam" in your email client.
- Delete the message.
- If you already clicked the link, scan your device for malware and monitor your bank statements.
Disclaimer: This assessment is based on pattern recognition and general knowledge, not live forensics. Always verify independently via official channels. Do not rely solely on this analysis for irreversible actions.
Next steps
- Forward the original email to Netflix's official phishing reporting address if available.
- Check your recent bank transactions for any suspicious activity.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
The problem
Users struggle to distinguish between legitimate corporate communications and sophisticated phishing attempts or social engineering scams. Relying on gut feeling or embedded links often leads to credential theft, financial loss, and compromised accounts.
What it does
- Analyzes messages, emails, and URLs for common scam signals like lookalike domains, urgency triggers, and mismatched calls to action.
- Categorizes information into known facts, warning signs, and unknowns to provide a clear mental model of the threat.
- Assigns a concrete risk level (Low, Medium, High, or Uncertain) based on pattern recognition and security best practices.
- Generates safe, independent verification steps that bypass the suspicious content entirely.
Why this beats prompting it yourself
This skill enforces a skeptical security protocol that prevents the AI from being "hallucinated" into trusting the sender's claims. It systematically separates background knowledge from unverified input, ensuring the assessment is based on architectural patterns rather than surface-level text.
Use cases
- Verifying unsolicited "urgent" emails from banks, shipping companies, or government agencies.
- Evaluating too-good-to-be-true investment offers or work-from-home job postings.
- Checking if a website domain is a legitimate brand portal or a typo-squatting phishing site.
- Assisting users who may have already interacted with a link and need immediate damage control steps.
Known limitations
Cannot perform live forensics, click links to see final destinations, or verify sender IP addresses. Analysis is limited to the text and descriptions provided by the user.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 21 days ago
- Passed all security checks, Safe to install