AI Summary

Security researcher Gal Weizman of Forever Security revealed a new attack method called BragJack that hijacks AI assistants embedded in browsers via a single malicious extension. The proof‑of‑concept targeted five Chromium‑based browsers or their AI agents: Google Chrome’s Gemini Live, Perplexity’s Comet, Microsoft Edge, Opera Neon, and Anthropic’s Claude running in Chrome. Weizman demonstrated that the malicious extension can compromise each of these agents, showing the technique works across multiple popular browsers. The disclosure highlights a novel vector for compromising built‑in AI features through extension abuse.

AI summaries can be wrong sometimes—always verify important details using the source article.