#6
SecurityWeek
general
May 08, 2026 at 06:53 UTC
Vulnerability in Claude Extension for Chrome Exposes AI Agent to Takeover
By Ionut Arghire
AI Summary
A vulnerability in Anthropic's Claude Chrome extension allowed any other installed browser extension to inject prompts and hijack the Claude AI agent, stemming from lax extension permissions and improper trust implementation. The flaw is a concrete example of the prompt injection attack surface introduced by agentic AI browser integrations.
Relevance score: 75.0/100
Sponsored
Protect Your Business
Expert cybersecurity solutions to safeguard your organization from evolving threats.
Get Protected →