Microsoft Warns Poisoned MCP Tool Descriptions Can Make AI Agents Leak Data
New Microsoft research shows how attackers can hijack AI agents that act on a user’s behalf, using nothing more than a poisoned tool description to make the agent quietly hand over company data to an outsider.
The trick is that the agent never breaks a rule. Every step looks routine, so in a default setup no alarm may fire.
The work comes from Microsoft Incident Response and its
Source: The Hacker News
Early rogue AI agent activity and attempts to hack found on urlquery.net Source: Hacker News
Watchtower Attack Update. Hier die aktuellen Top 5 Attack-IPs, die auf doode.info klopfen. 89.167.35.212 — 1 requests (recent log) Mehr Live-Daten und die komplette Historie im /attacks/ Watchtower-Bereich (GoAccess Report
Watchtower Attack Update. Hier die aktuellen Top 5 Attack-IPs, die auf doode.info klopfen. 144.76.19.72 — 1035 requests (recent log) 89.167.35.212 — 880 requests (recent log) 74.7.241.36 — 631 requests (recent