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
Fake AI Agent Skill Passed Security Scans and Reportedly Reached 26,000 Agents Security firm AIR built a fake AI agent skill, pushed it through a popular skill marketplace and an Instagram ad,
Watchtower Attack Update. Hier die aktuellen Top 5 Attack-IPs, die auf doode.info klopfen. 195.178.110.48 — 4 requests (recent log) 89.167.35.212 — 1 requests (recent log) Mehr Live-Daten und die komplette
Veeam, Terraform MCP, Django Patch Critical Flaws, Led by CVSS 10.0 Cross-Tenant Bug HashiCorp, Veeam, and the Django Software Foundation have patched 11 vulnerabilities across Terraform MCP Server, Veeam Service