Productivity · Tabnews · 🇧🇷 Brazil
Use a local AI to detect phishing
A security professional showed a Python script using a local model to analyze the intent of suspicious emails.
- Profession
- Security Analyst, Developer
- Tools
- Ollama, Python
- Source
- tabnews.com.br ↗
- Country
- 🇧🇷 Brazil
- Report date
- May 7, 2026
- Verified on
- October 24, 2026
What they did
Created a script that asks a local model to assess the urgency, request and context of emails.
How it went
The account gives no numbers.
Good to know
Running locally avoids sending emails (personal data) to third parties.
The prompt
Analyze this email [text]. Assess: sender, urgency, call to action, links and tone. Give a risk score from 0 to 10 and explain it in 3 lines. Don't click on anything.
Replace what is in [brackets]. Prompt written by us from the account, not a literal copy of the source. Do not paste other people’s personal data (privacy laws such as LGPD and GDPR apply).
Summary in our own words. Results as stated in the original account; we have not tested or audited them. Read the source ↗ Found a mistake?
Similar cases
01When your AI limit runs out in the middle of the day
A dev running four subagents across four repositories ran out of tokens and reflected on their dependence on AI.
02Running an offline AI assistant on your iPhone
A dev built Anvil, which runs models on the device for use on a plane, on the subway or without roaming.
03Estimating how long your AI plan will last before it runs out
A dev published an open calculation to estimate how many tokens fit into the Pro/Max plans.
04Building a "thinking system" with Obsidian and Claude
A developer started recording what he learns in Obsidian and using Claude to connect notes.
05Sending AI summaries and research straight to your Kindle
A developer built a Go MCP in minutes that lets Claude or Codex send texts to a Kindle.
06Setting up complete Discord servers with an AI bot
An open source bot uses Gemini to plan categories, channels, roles and rules from a description.
07Stopping your WhatsApp agent from duplicating customers in the CRM
A post shows why agents write to the wrong record: accents, invisible characters and stylized names.
08Generating all of a game's pixel art with code written together with AI
A dev gave up on image generators and started drawing isometric sprites with a Python script.