• Aim Labs has identified a critical zero-click AI vulnerability, dubbed “EchoLeak”, in Microsoft 365 (M365) Copilot and has disclosed several attack chains that allow an exploit of this vulnerability to Microsoft's MSRC team.
• This attack chain showcases a new exploitation technique we have termed "LLM Scope Violation" that may have additional manifestations in other RAG-based chatbots and AI agents. This represents a major research discovery advancement in how threat actors can attack AI agents - by leveraging internal model mechanics.
• The chains allow attackers to automatically exfiltrate sensitive and proprietary information from M365 Copilot context, without the user's awareness, or relying on any specific victim behavior.
• The result is achieved despite M365 Copilot's interface being open only to organization employees.
• To successfully perform an attack, an adversary simply needs to send an email to the victim without any restriction on the sender's email.
• As a zero-click AI vulnerability, EchoLeak opens up extensive opportunities for data exfiltration and extortion attacks for motivated threat actors. In an ever evolving agentic world, it showcases the potential risks that are inherent in the design of agents and chatbots.
• Aim Labs continues in its research activities to identify novel types of vulnerabilities associated with AI deployment and to develop guardrails that mitigate against such novel vulnerabilities.
  Aim Labs is not aware of any customers being impacted to date.
  TL;DR
  Aim Security discovered “EchoLeak”, a vulnerability that exploits design flaws typical of RAG Copilots, allowing attackers to automatically exfiltrate any data from M365 Copilot’s context, without relying on specific user behavior. The primary chain is composed of three distinct vulnerabilities, but Aim Labs has identified additional vulnerabilities in its research process that may also enable an exploit.

Since early March 2025, Volexity has observed multiple suspected Russian threat actors conducting highly targeted social engineering operations aimed at gaining access to the Microsoft 365 (M365) accounts of targeted individuals. This activity comes on the heels of attacks Volexity reported on back in February 2025, where Russian threat actors were discovered targeting users and organizations through Device Code Authentication phishing...

Starting in mid-January 2025, Volexity identified several social-engineering and spear-phishing campaigns by Russian threat actors aimed at compromising Microsoft 365 (M365) accounts. These attack campaigns were highly targeted and carried out in a variety of ways. The majority of these attacks originated via spear-phishing emails with different themes. In one case, the eventual breach began with highly tailored outreach via Signal.Through its investigations, Volexity discovered that Russian threat actors were impersonating a variety of individuals

Over the past few days, we have seen phishing attacks that use a combination of compromised Microsoft 365 accounts and .rpmsg encrypted emails to deliver the phishing message.

Revendiquée par un cyberpirate dénommé Anonymous Sudan, une série d'attaques a paralysé pendant plusieurs jours de multiples services cloud de Microsoft dont Outlook, SharePoint et OneDrive. Les difficultés de l'éditeur à assurer une remise en service complète dans ce laps de temps interroge.

Today, CISA released the Untitled Goose Tool to help network defenders detect potentially malicious activity in Microsoft Azure, Azure Active Directory (AAD), and Microsoft 365 (M365) environments. The Untitled Goose Tool offers novel authentication and data gathering methods for network defenders to use as they interrogate and analyze their Microsoft cloud services. The tool enables users to: