Microsoft Prompt Injection Vulnerability

Microsoft security researchers have identified "AI Recommendation Poisoning," an attack exploiting specially crafted URLs or embedded prompts to inject persistent, biasing instructions into AI assistant memory. This technique, categorized under MITRE ATLAS® AML.T0080, can compromise AI objectivity, leading to subtly manipulated recommendations in critical domains like finance, health, and security.

What Happened

Microsoft security researchers have identified "AI Recommendation Poisoning," an attack exploiting specially crafted URLs or embedded prompts to inject persistent, biasing instructions into AI assistant memory. This technique, categorized under MITRE ATLAS® AML.T0080, can compromise AI objectivity, leading to subtly manipulated recommendations in critical domains like finance, health, and security.

Why This Matters

The evidence matters to defenders using Microsoft because it may let untrusted content influence connected tools or sensitive workflows.

Recommended Action

No confirmed vendor remediation is available in the current evidence. Confirm whether Microsoft is present in your environment and review the affected configuration.

Exposure

Exposure reason: This incident does not currently match a technology in My AI Stack.

Exploitation status: UNKNOWN

Primary entities:

Timeline

• Incident first seen
  Feb 10, 2026 05:30

  BugSkan first recorded this incident.

• Manipulating AI memory for profit: The rise of AI Recommendation Poisoning - Microsoft
  Feb 10, 2026 05:30

  microsoft.com · Research

Sources

My AI Stack Match