BREAKING
Microsoft Warns: Hidden MCP Instructions
How the Tool-Poisoning Attack Works
1Agent loads tool description
2Hidden instructions embedded
3Agent treats them as legit
4Data sent outward
0
unpaid invoices leaked
Injection Success: 50%+ vs Under 2%
No mitigation50
With Spotlighting2
Microsoft's Mitigation Toolkit
DetectionPublic Preview
Agent Governance Toolkit
Prompt Shields
Work IQ MCP
Control
Human-in-the-Loop approvals
Purview DLP
Entra Agent ID
Least Agency Now Key for Agents
AI NEWS BLITZ
Microsoft warns that hidden instructions in MCP tools can hijack AI agents.