Aim Labs discovered a zero-click AI vulnerability named “EchoLeak” in Microsoft 365 Copilot and reported several ways to exploit it to Microsoft’s MSRC team.
The new attack method called “LLM Scope Violation” has been identified, which could also impact other RAG-based chatbots and AI agents. This finding marks a significant breakthrough in understanding how attackers can exploit AI agents by using their internal mechanics.
By infosecbulletin
/ Monday , October 5 2026
Citrix has put out emergency security updates for a NetScaler SAML flaw that hackers are using. Known as CVE-2026-88779, this...
Read More
By infosecbulletin
/ Monday , October 5 2026
Hackers got into the identity and access management system at the Technical University of Denmark (DTU) and downloaded a lot...
Read More
By infosecbulletin
/ Sunday , October 4 2026
Microsoft's official X account was taken over to promote an unapproved Clippy-themed cryptocurrency. The tech giant’s X account, with 13...
Read More
By infosecbulletin
/ Saturday , October 3 2026
CPanel has put out security updates to fix three problems in cPanel & WHM. These problems could let attackers take...
Read More
By infosecbulletin
/ Friday , October 2 2026
Nearly 100,000 Bee Cheng Hiang customers had their email addresses leaked when an employee used an AI tool to generate...
Read More
By infosecbulletin
/ Thursday , October 1 2026
Hackers to exploit a flaw in Zimbra mail servers that are connected to the Internet. They send special emails that...
Read More
By infosecbulletin
/ Wednesday , September 30 2026
Google has said that hackers are using two serious Citrix NetScaler security holes to get root access, set up hidden...
Read More
By infosecbulletin
/ Wednesday , September 30 2026
The U.S. Cybersecurity and Infrastructure Security Agency (CISA) is alerting people about a major flaw in MikroTik RouterOS. This could...
Read More
By infosecbulletin
/ Tuesday , September 29 2026
Apple has launched iOS 26.7.1 and iPadOS 26.7.1 to fix a serious zero-day flaw that it believes might have been...
Read More
By infosecbulletin
/ Tuesday , September 29 2026
The JadePuffer ransomware group is attacking Azure users with agent-based attacks that gather information, steal passwords, and damage key components. The...
Read More

By using chains, attackers can automatically and unnoticed extract sensitive information from M365 Copilot, avoiding reliance on user 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. To read the full report click here.
40,000 + live internet cameras exposed globally !