{% extends "base.html" %} {% block title %}SentinelAI Cyber Assistant — Phishing & Scam Risk Scanner{% endblock %} {% block meta_description %}Paste a URL, email, or message to receive a privacy-safe 0–100 phishing risk score with clear explanations.{% endblock %} {% block content %}
Privacy-first cyber defense

Detect phishing URLs and scam messages before they reach people.

SentinelAI gives every submission a 0–100 risk score, explains the strongest signals, and stores only privacy-safe metadata for your dashboard.

URL phishing detection Scam message NLP Explainable AI
Live risk console
{{ avg_score }} avg risk
{{ total_scans }}Scans
{{ high_risk_count }}High risk
v1Model
Local in-memory analysis
False-positive review dashboard
Threat explanations included
First workflow

Scan a suspicious URL, email, or message

This MVP uses a local heuristic/NLP engine as the safe baseline before adding trained Scikit-learn models and public cybersecurity datasets.

{% csrf_token %} {% if form.non_field_errors %}
{{ form.non_field_errors }}
{% endif %}
{{ form.scan_type.label }}
{% for radio in form.scan_type %} {% endfor %}
{% for error in form.scan_type.errors %}
{{ error }}
{% endfor %}
{{ form.content }} {% for error in form.content.errors %}
{{ error }}
{% endfor %}
Security posture

Built for sensitive submissions

01

Raw content stays out of storage

Only a sanitized preview, SHA-256 hash, risk score, and explanation are persisted.

02

Explainable decisions

Every result lists weighted indicators so users can understand what triggered the score.

03

ML-ready pipeline

The scanner interface is ready to blend in trained models, evaluation metrics, and safe updates.

Threat dashboard

Recent detections

Open full history
{% if recent_scans %} {% else %}

No scans yet

Run your first URL or message scan to populate the dashboard.

Start scanning
{% endif %}
{% endblock %}