"Within Anthropic, we've seen appreciable improvements using early versions of Claude for Chrome to manage calendars, schedule meetings, draft email responses, handle routine expense reports, and test new website features.
However, some vulnerabilities remain to be fixed before we can make Claude for Chrome generally available. Just as people encounter phishing attempts in their inboxes, browser-using AIs face prompt injection attacks—where malicious actors hide instructions in websites, emails, or documents to trick AIs into harmful actions without users' knowledge (like hidden text saying "disregard previous instructions and do [malicious action] instead").
Prompt injection attacks can cause AIs to delete files, steal data, or make financial transactions. This isn't speculation: we’ve run “red-teaming” experiments to test Claude for Chrome and, without mitigations, we’ve found some concerning results.
We conducted extensive adversarial prompt injection testing, evaluating 123 test cases representing 29 different attack scenarios. Browser use without our safety mitigations showed a 23.6% attack success rate when deliberately targeted by malicious actors."
https://www.anthropic.com/news/claude-for-chrome