Microsoft Fixes Zero-Click Vulnerability in Copilot AI

Jun 13, 2025
Microsoft has addressed a critical zero-click vulnerability in its Copilot AI system, discovered by Aim Security, which could have allowed data leaks without user interaction.

Microsoft Corporation has resolved a critical security flaw in its Copilot AI system, identified by Aim Security, a Tel Aviv-based cybersecurity firm. The vulnerability, known as EchoLeak, was characterized as a 'zero-click' flaw, meaning it could be exploited without any user interaction, according to Inc.

The EchoLeak vulnerability, assigned the identifier CVE-2025-32711, allowed unauthorized access to sensitive data within Microsoft 365 Copilot's context. This flaw was particularly dangerous as it enabled attackers to exfiltrate data without user awareness or action. The attack involved embedding malicious prompts in seemingly benign content, such as emails, which the AI system would process, leading to unintended data leaks.

Microsoft has already addressed the issue server-side, ensuring that no customer action is required. The company confirmed that there was no evidence of the vulnerability being exploited in the wild. This incident highlights the potential risks associated with AI systems and the importance of ongoing vigilance in cybersecurity measures.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Cybersecurity AI Weekly or Daily AI Brief.

Also, consider following us on social media:

Cybersecurity AI AI Brief AI Brief (X)
Free newsletter

Cybersecurity AI Weekly

Weekly newsletter about AI in Cybersecurity.

Guide
AI app builders

AI app builders

Tools that turn a description into a working web or mobile app, and the platforms companies use to build internal tools with AI

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.