Last seen August 18, 2026

AI Prompt Injection Vulnerability

Microsoft Copilot inadvertently revealed its secret input prompts, creating a critical information disclosure vulnerability. This prompt leakage allowed adversaries to exploit the AI model's underlying configuration, compromising its intended behavior.

Technical Severity
Low severity
Lifecycle Status

NEW

What Happened

Microsoft Copilot inadvertently revealed its secret input prompts, creating a critical information disclosure vulnerability. This prompt leakage allowed adversaries to exploit the AI model's underlying configuration, compromising its intended behavior.

Why This Matters

Current evidence identifies a security issue involving the affected technology, but does not yet support a more specific impact claim.

Recommended Action

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

Exposure

My AI Stack Exposure

Exposure unknown

Recommended Response
Last Seen

Aug 18, 2026 05:30

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

Exploitation status: UNKNOWN

Primary entities:

MicrosoftMicrosoft CopilotPrompt Injection

Timeline

  • Incident first seen
    Aug 18, 2026 05:30

    BugSkan first recorded this incident.

  • Microsoft Copilot reveals secret input that allowed it to be hacked - Ars Technica
    Aug 18, 2026 05:30

    arstechnica.com · Research

Sources

Microsoft Copilot reveals secret input that allowed it to be hacked - Ars Technica

arstechnica.com · Aug 18, 2026 05:30

Microsoft Copilot inadvertently revealed its secret input prompts, creating a critical information disclosure vulnerability. This prompt leakage allowed adversaries to exploit the AI model's underlying configuration, compromising its intended behavior.

Open publisher source

My AI Stack Match

Want personalized relevance?

Create an account to see which incidents overlap with your AI stack.

← Back to incident intelligence