Developer Builds Free AI-Powered API That Detects Phishing Sites and Prompt Injection
A solo developer from Punjab, India has built PhishVision, a free REST API that detects phishing websites using AI vision rather than relying on URL reputation databases. The tool launches a headless Chromium browser, captures a screenshot of the target page, and extracts all visible and hidden text before sending both to a Vision AI model for analysis. This approach allows it to flag brand-new phishing sites that have not yet appeared in any known threat database. PhishVision also addresses a growing attack vector called prompt injection, where malicious instructions are hidden in webpages using invisible text to manipulate AI agents and chatbots. The API returns a structured JSON verdict including confidence score, impersonated brand, threat type, and detected visual anomalies, and is accessible live at OpticParse.com.
This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)
Log in to join the discussion and vote.
Log in