AI-powered email phishing detection using a private, local LLM. No data leaves your device. Supported Local LLM Providers: - Ollama - LM Studio - llama.cpp server - vLLM - etc.
Versie-informatie
Versie 1.0.6
49.3 KiB
Werkt met
Thunderbird 115.0 en hoger
v1.0.6 - False Positive Reduction Update Changes Made 1. Added "Suspicious" Verdict Category - New verdict: suspicious - for borderline emails that aren't clearly malicious - Three-tier system: legitimate → suspicious → malicious - UI shows orange badge with "⚡ SUSPICIOUS" for this category 2. Enhanced System Prompt with Legitimate Email Patterns Added guidance for the LLM to recognize legitimate emails: - Mailing list headers (newsletters) - No credential requests - Links matching sender domain - Transactional emails (receipts, confirmations) - Personalized greetings 3. Mailing List Recognition - Emphasized is_mailing_list: true as a strong legitimate indicator - Prompt explicitly states "newsletters are typically legitimate" 4. Confidence Threshold Logic - Low-confidence "malicious" verdicts (< 70%) automatically downgraded to "suspicious" - Adds explanatory reason when adjustment occurs 5. Reply-To/Return-Path Context - Clarified these mismatches are common in legitimate newsletters - "Only suspicious when combined with phishing content" 6. Updated UI - New orange "warning" badge style for suspicious emails - Pulsing animation to draw attention without alarming Files Modified | File | Changes | |------|---------| | src/shared/state.js | Added 'suspicious' to VERDICTS array | | src/shared/api.js | New prompt, confidence threshold logic | | src/messageDisplay/inject.js | 3-tier verdict display logic | | src/messageDisplay/inject.css | Orange warning badge styling | | manifest.json | Version 1.0.6 | | package.json | Version 1.0.6 | Expected Impact - Fewer legitimate emails marked as "malicious" - Borderline cases now show "suspicious" instead of binary verdict - Newsletters and mailing lists less likely to trigger false positives - Low-confidence detections handled more gracefully
Sommige add-ons vragen toestemming om bepaalde functies uit te voeren (voorbeeld: een tabblad-add-on vraagt toestemming voor toegang tot het tabbladensysteem van uw browser).
Aangezien u de controle over uw Thunderbird hebt, is de keuze om deze aanvragen toe te kennen of te weigeren aan u. Het accepteren van toestemmingen heeft in principe geen gevolgen voor de prestaties of beveiliging van uw browser, maar in zeldzame gevallen kan er sprake zijn van een risico.
Add-ons
