tenetsecurity.aitalkAgentjacking: How We Hijacked AI Agents Inside a $250B Company
Agentjacking is an attack by Tenet Security researchers in which a fake bug report or poisoned log makes an AI coding agent run attacker code during a routine triage request. They report an 85% success rate against Cursor, Claude Code and Codex, including network-disabled sandboxes, and confirmation across 2,388 organizations. The recording covers sandbox and container bypasses and defenses, including the open-source JackStop hardening tool.
TL;DR Webinar walkthrough of agentjacking, where a poisoned bug report hijacks AI coding agents into remote code execution, with sandbox bypasses and the JackStop defense tool.
Organisations named here
- agentjacking
- JackStop
Technologies named here
- Cursor
- Claude Code
- Codex
- Tenet Security
- AI coding agents at a $250 billion company
- JackStop
Techniques named here
- Agentjacking
- Sandbox escape
- Sandbox and container bypass
Related in AI Security
blog.talosintelligence.comtoolIntroducing CAIRN: Frontier tracking for AI-integrated malware (Cisco Talos)
github.comadvisoryFlowise MCP Security Bypass Enables RCE
github.comrepoYesWeHack Claude Kit
jfrog.comarticle