Text & Scam Signals
Language-based trust scoring for social engineering and scam scenarios.
Decide if message intent looks manipulative before you reply, click, or pay.
Use cases: Social engineering triage • Marketplace chat moderation • High-risk outreach screening
Several of these pages share one keyword-and-pattern scorer with different overlays. Treat a “high risk” flag as a reason to pause, not as proof of fraud. For lists, use the bulk analyzers on the Trust tools index.
AI Text Detector
Rough AI-likeness + spam density for triage — not academic authorship proof; combine with scenario-specific checkers below.
Fake Job Offer Text Checker
Recruitment fraud: upfront fees, vague roles, and data-harvest asks before any real interview process.
Romance Scam Text Checker
Isolation, urgency, and money-move patterns typical in romance/crypto pig-butchering chats.
Investment Scam Text Checker
Guaranteed returns, secrecy, and off-platform funding — language signals before someone sends crypto or wire.
Marketplace Fraud Text Checker
Off-platform payment, fake escrow, and shipping tricks in peer-to-peer commerce chats.
Urgency and Pressure Language Checker
Generic pressure detector usable across channels — “act now or lose access” without verifiable context.
Rental Scam Text Checker
Deposit-before-viewing, wire-to-random-account, and cloned listing patterns in rental mail threads.
Charity Scam Text Checker
Emotional urgency plus untraceable payment asks pretending to be disaster or crisis relief.
Social Proof Authenticity Checker
Testimonials that are too generic, duplicated, or mismatched to the product — common on scam landers.
Account Recovery Scam Checker
Fake “verify your account” and password-reset pressure that bypasses real issuer flows.
Impersonation Tone Checker
Boss/IT/support voice with unusual channels (WhatsApp, personal email) and payment asks.
AI Paraphrase Detector
Flags unnatural rewrite-heavy text that may hide copied policies or phishing body content.
Spam Phrase Density Checker
Quantifies boilerplate manipulation phrases — useful for outbound review and chat moderation queues.
Credential Harvest Language Checker
Identifies wording that pressures users to reveal passwords, OTPs, or recovery data outside official flows.
Fake Support Conversation Checker
Screens support-style chats for impersonation scripts, remote-access pushes, and payment extraction tactics.
Giveaway Scam Text Checker
Detects fake prize and giveaway messaging patterns that push urgent links or fee-before-claim steps.
Blackmail Extortion Text Checker
Flags coercive threats and extortion framing in messages so teams can escalate safely and avoid panic responses.
Package Delivery Scam Checker
Checks parcel-notification texts for fake courier links, fee traps, and account-hijack pretexts.
Tax Penalty Threat Text Checker
Detects fake tax authority threats that use urgency and penalties to force immediate payment.
Fake Bank Alert Text Checker
Screens bank-alert style messages for account panic scripts and credential-harvest call-to-actions.
Remote Job Advance Fee Checker
Identifies remote-job scam cues where applicants are asked to pay upfront for equipment, onboarding, or access.
Social Media Impersonation Checker
Evaluates profile and message tone cues that indicate impersonation of brands, creators, or support agents.
Authority Impersonation Checker
Detects police, government, or regulator impersonation language used to pressure urgent compliance or payment.