BragJack: Single Browser Extension Hijacks AI Agents Across Five Major Platforms
Sign in✓ Signed in
Researchers at Forever Security have disclosed a novel attack technique that allows a single malicious browser extension to commandeer AI assistants across Chrome, Microsoft Edge, Opera Neon, Perplexity Comet, and Claude in Chrome. The proof-of-concept attacks, demonstrated by researcher Gal Weizman, bypass traditional security guardrails by targeting the privileged communication channels between browser AI components and their remote services, rather than attempting to manipulate the AI models themselves.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...