This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle
What I Built
PhishBrief AI is a local-first AI-powered phishing analysis tool designed to help small businesses and individuals understand suspicious emails and messages before interacting with them.
Phishing emails often use urgency, impersonation, suspicious links, and requests for sensitive information to trick people. Many small teams lack dedicated security staff or enterprise-grade email security tools.
PhishBrief AI aims to make initial phishing analysis more accessible by helping users examine suspicious content, understand potential warning signs, and receive actionable security recommendations.
The project explores a privacy-conscious approach: running an open-weight AI model locally instead of requiring every message to be sent to a hosted AI API.
Who could benefit?
Small businesses without a dedicated security operations team
Freelancers and independent professionals
Students learning email security and phishing detection
IT support teams that need an accessible first-pass analysis tool
The long-term side-hustle opportunity is a lightweight security assistant for small teams that need understandable phishing triage without the cost or complexity of a full enterprise security platform.
Demo
Watch the demo: https://www.loom.com/share/ca8e3321c0274ec49f58d0d423f2813b
The demo shows the application running locally and demonstrates its phishing-analysis workflow.
Code
GitHub repository:
https://github.com/devanshshukla-3004/PhishBrief-AI
Explore the source code, setup instructions, and project implementation in the repository.
How I Built It
PhishBrief AI combines a Python application with local AI inference through Ollama.
Core technologies
Python — application logic and analysis workflow
Streamlit — interactive user interface
Ollama — local model runtime
Granite 3.2 Vision — the configured open-weight model used for local inference
The development setup also includes Gemma 3 1B as another locally available model.
The workflow is designed around analyzing user-provided suspicious content, identifying potential phishing indicators, explaining the associated risks, and presenting recommendations in a more understandable format.
The emphasis is on making AI-assisted security analysis accessible while exploring local inference as an alternative to sending potentially sensitive content to a third-party AI API.
This is an assistive analysis tool, not a guarantee that every phishing attempt will be detected. Users should still verify suspicious messages and links independently.
**
Why Does Open Innovation Matter?**
Open innovation makes projects like PhishBrief AI possible for developers who do not have access to expensive infrastructure or enterprise security systems.
Open-weight models and tools such as Ollama make it possible to experiment with local inference, learn how AI systems behave, and build practical applications around them.
For this project, local inference offers three important advantages:
Privacy-conscious experimentation: Potentially sensitive email content can be processed locally, depending on the application's implementation and configuration.
Lower barriers to development: Developers can experiment without depending entirely on paid, hosted AI APIs.
Customisation and learning: Open-weight models make it easier to explore model choices, prompting strategies, and application workflows.
Open innovation does not automatically guarantee security or accuracy, but it gives independent developers more control over how AI-powered tools are built and evaluated.
My First User
My first target users for PhishBrief AI are individuals and small-business teams who need a simple way to understand suspicious emails without requiring advanced cybersecurity knowledge.
I'm looking for early testers who can try the tool with safe sample phishing emails, evaluate whether the risk explanations are understandable, and share feedback on its usefulness and ease of use.
The goal is to learn whether local AI-powered phishing analysis can make basic security triage more accessible to people without a dedicated security team.
I'm currently looking to gather feedback from early users and improve the project based on their experience.
Prize Categories
PhishBrief AI is my submission to the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle.
The project focuses on building a practical AI-powered tool around open-weight models and local inference.
Top comments (0)