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. 74.7.227.2 — 1146 requests (recent log) 213.209.159.175 — 263 requests (recent log) 89.167.35.212 — 246 requests (recent
Mustang Panda Uses Zoho WorkDrive as Command Channel in Indian Government Attacks The China-aligned espionage group Mustang Panda is running two campaigns against the Indian government and hydropower targets, deploying new malware
Cyberdecks, going analog, and convivial technology Source: Hacker News