Researchers demonstrate how # Agentjacking can use one fake Sentry bug report to trick AI coding agents into running code on a developer’s machine, exposing ris
Researchers have demonstrated a new attack method called Agentjacking, which exploits AI coding agents. By submitting a fake Sentry bug report, attackers can trick these agents into executing malicious code on a developer's machine. This vulnerability poses a significant risk to development teams utilizing AI coding assistants like Claude Code and Cursor. AI
IMPACT Highlights potential security risks in AI coding assistants, necessitating enhanced security measures for developers.