← back
x.comm4rioFri, Jun 5, 2026, 12:47 AM PDT
score 16.6
188likes24RT1reply

Attackers trick AI coding agents into running malicious commands

Original: 🚨 TL;DR: Attackers are sending fake Sentry bug alerts to projects using public Sentry DSNs. The fake alert is designed to trick AI agents into running a malicious `npx` command that looks like a Sent

Source: x.com

Writing ELI5 summary…