Agentjacking: How a Fake Sentry Bug Report Hijacks Your AI Coding Agent
AI security
agentjacking
MCP security
A new attack called agentjacking uses public Sentry DSNs and MCP to inject malicious instructions into Claude Code, Cursor, and Codex - then exfiltrates your AWS keys, GitHub tokens, and git credentials. 85% success rate, 2,388 orgs exposed, zero authentication needed.