Library Header Image Library Header Image

When AI Agents Become Backdoors: The New Era of Client-Side Threats


Posted on in Presentations

This session will share details of critical vulnerabilities discovered across every major AI platform: Cursor, Anthropic Claude Code, OpenAI Codex CLI, Google Gemini CLI affecting hundreds of millions of users. These flaws transform trusted AI tools into persistent backdoors. Vulnerabilities are being fixed following responsible disclosure. Will include live demos and actionable security insights.

Access This and Other RSAC™ Conference Presentations with Your Free RSAC Membership

Your RSAC™ Membership also includes AI-powered summaries, mind maps, and slides for Conference presentations, Group Discussions with experts, and more.

Watch Now >>
Participants
Oded Vanunu

Speaker

Chief Technologist, Check Point Software


Share With Your Community