BragJack

highMalware

BragJack Proof-of-Concept Hijacks AI Browser Assistants via Malicious Extensions

A proof-of-concept attack dubbed BragJack, disclosed by researcher Gal Weizman of Forever Security, exploits AI assistant integrations in Chrome, Microsoft Edge, Opera Neon, Perplexity Comet, and Claude in Chrome. Using a single malicious extension, the Prompt Forcing technique can hijack these assistants to inject instructions or exfiltrate data. The research earned over $20,000 in bounties and two CVE assignments (CVE-2026-XXXX, CVE-2026-YYYY). Vendors are likely reviewing or deploying mitigations.

BleepingComputer10 days ago1 min read

highCyber Attacks

BragJack Attack Turns Browser AI Assistants into Malicious Agents

Researchers have disclosed a novel attack vector, dubbed BragJack, that hijacks the agentic AI assistants embedded in web browsers. The attack can trick these AI systems into accessing sensitive information, performing malicious actions on behalf of the user, and exfiltrating data. While specific technical details and affected browsers remain unconfirmed, the discovery highlights emerging risks as AI assistants become more autonomous.

Dark reading13 days ago1 min read

BragJack

Quick answers

Related Articles

BragJack Proof-of-Concept Hijacks AI Browser Assistants via Malicious Extensions

BragJack Attack Turns Browser AI Assistants into Malicious Agents