Guardio’s VibeScamming Benchmark tests how AI agents like ChatGPT, Claude & Lovable can be abused to create phishing attacks with just a few prompts.

Guardio's platform is a resource for cybersecurity professionals and internet users, offering insights into online security threats, malware protection, and data privacy. Through articles, security alerts, and educational resources, Guardio offers insights into common cybersecurity risks, security best practices, and digital hygiene habits. Readers can learn about protecting their devices from malware, securing their online accounts, and staying safe while browsing the internet to mitigate cyber threats and safeguard their personal information.

Guardio

VibeScamming refers to using AI for generating phishing scams with minimal skill required. Guardio Labs developed the VibeScamming Benchmark to evaluate AI resistance against misuse in phishing workflows. The benchmark's first round tested ChatGPT, Claude, and Lovable, highlighting their varying degrees of resilience. The results reveal important insights into the balance between AI capabilities and their potential abuses, stressing the need for robust safety measures.

VibeScamming — From Prompt to Phish: Benchmarking Popular AI Agents’ Resistance to the Dark Side

Test Subjects — From Top Players to Newcomers