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
Watchtower Attack Update. Hier die aktuellen Top 5 Attack-IPs, die auf doode.info klopfen. Keine relevanten IPs erfasst (ruhig oder stark gefiltert). Mehr Live-Daten und die komplette Historie im /attacks/ Watchtower-Bereich
⚡ Weekly Recap: WordPress RCE, SonicWall 0-Days, AI Service Attacks, SharePoint 0-Day and More A single request should not be able to do this much. But this week, small inputs
Critical Rails Flaw Could Let Unauthenticated Attackers Read Server Files via Image Uploads Ruby on Rails has released fixes for a critical Active Storage vulnerability that could let unauthenticated attackers