How does it catch grammatically perfect AI-crafted mail?

It splits analysis into V-Triad pressure plus broken Japanese, and separately flags sterile polite tone, rigid structure, missing live context, and sudden money-demand divergence.

Which attack scenarios ship as presets for testing?

Fake police, fake support warnings, CEO secret remittance, tax seizure notice, fake SSO reset, plus a benign office message as the safe baseline.

What is the counter-measure panel actually showing?

It shows exception-injection replies such as asking for affiliation, meeting at a police window, or confirming codes internally, which break scripted or bot-driven attacker flows.

Do I need a Gemini API key to run the analysis?

No. Judgment uses @typesafe-ai/sdk with your TypeSafe key on an Express backend; no Gemini key is required for full operation.

What are the two spectra it evaluates?

Spectrum 1 covers traditional social engineering, including Authority, Fear and Urgency plus awkward Japanese. Spectrum 2 covers GenAI anomalies: Vanilla Tone, Structural Rigidity, Temporal Blindness, and Emotional Inflation.

What do the threat score bands mean?

On a 0 to 100 scale: Safe is 0-20, Suspicious is 21-60, and Malicious is 61-100. The gauge and spectrum breakdown display the per-vector probabilities behind the total.

What runtime and license does the app have?

Node.js v20.0.0 or newer, with the dev server on port 3000 by default and PORT configurable. The project is MIT-licensed and requires only a TypeSafe key to run.

CommunityJev Tools & CLIs

JEV-Dual-Spectrum-Phishing-Guardian

Japanese-focused phishing analyzer scoring messages on classic pressure tactics and GenAI tells, with a 0-100 threat gauge and report export.

See highlights

Open github.com

Stars: 0
Language: TypeScript
Published by: Community
Author: YuyaForest
Last verified: Oct 2026

YuyaForest/JEV-Dual-Spectrum-Phishing-Guardian

User repository on GitHub

View on GitHub

Powered by TypeSafe AI (JEV System One) High-Speed Inference Engine, Fraud and Targeted Phishing Detection / Dual-Spectrum Analysis Platform for Conventional Social Engineering (V-Triad) and Generative AI Spoofing Risks

Forks: 0
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

Tagscommunity github

Works forJev for Moderation

Used inJev for Software & DevTools

Languages: TypeScript

Highlights

Dual spectra cover authority, fear, urgency, and unnatural Japanese alongside four GenAI anomaly signals.
Threat score bands safe 0-20, suspicious 21-60, and malicious 61-100 with per-vector probability bars.
React dashboard with threat gauge, spectrum breakdown, diagnostics drawer, and Markdown report copy.
Node 20+ setup with Express backend and six built-in fraud and benign verification scenarios.

Watch out

Rule-based threat bands over model scores; verify presets against your own messages before operational use. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

OmniStudio

197

A Chinese-first desktop workbench for local models whose JEV page runs typed noul, choice and score questions against a local engine or a cloud key, alongside a gateway, RAG knowledge base and shared memory.

Jev Tools & CLIs#community#jevbest

Community

kunpengtalk/OmniStudioTypeScript

jev-recall

Python memory filter that judges every stored memory against the current request with one calibrated yes/no per memory in a single Jev request, keeping everything above a threshold.

Jev Tools & CLIs#community#jevbest#catalog-import

Community

samdotmak/jev-recallTypeScript

sharp

Browser extension that filters your X timeline with a model you choose and pay for, using plain-language rules plus per-author and blocked-word controls.

Jev Tools & CLIs#community#jevbest#catalog-import

Community

tshmieldev/sharpTypeScript

Jevest

GitHub Action that reviews pull requests with a read-only finder agent plus a refuting verifier, using Jev only to triage, route, label, and gate merging.

Jev Tools & CLIs#community#github

Community

tincke10/JevestTypeScript

chess-with-jev-

Hybrid chess experiment pairing Jev strategic candidate selection with a deterministic alpha-beta search engine inside a Chrome extension that plays on Chess.com with live telemetry.

Jev Tools & CLIs#community#github

Community

Deepender25/chess-with-jev-TypeScript

mood-pixels

Tiny mood tracker: write a few words about your day and Jev returns one of five moods plus an energy score and self-care nudge, plotted on a Year in Pixels calendar stored in the browser.

Jev Tools & CLIs#community#github

Community

mahshid/mood-pixelsTypeScript

From the Jev guides

Original write-ups on what this entry is for.

Jev on the Gateways: Vercel, Workers AI, and OpenRouter

Oct 12, 2026

The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.

Jev Tools & CLIs#gateway#vercel#cloudflare

Read article

Exporting Decision Models: GGUF, ONNX, and Device Runtimes

Oct 10, 2026

Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.

Jev Tools & CLIs#open-models#local#onnx

Read article

Records at Rest: Documents, Inboxes, and Risk Queues

Sep 28, 2026

Jev labels a record that already exists. Code moves, flags, or holds it. How the document, mail, and transfer tools keep the action out of the model.

Jev Tools & CLIs#classification#email#security

Read article

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai