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
/ Tuesday , June 23 2026
A cyber attack seems to have affected one of India's top electronics companies. Tata Electronics has said there was a...
Read More
By infosecbulletin
/ Monday , June 22 2026
The recent finding shows how powerful Mythos is: the AI can access the US government's secret networks in just a...
Read More
By infosecbulletin
/ Monday , June 22 2026
Test before going live is important for AI developers. But there's a problem: testing usually uses fake scenarios that often...
Read More
By infosecbulletin
/ Sunday , June 21 2026
AryStinger has taken control of over 4,000 old D-Link routers to use them as proxies for harmful traffic. The team...
Read More
By infosecbulletin
/ Sunday , June 21 2026
Brazil's government suspects a hacking attack triggered an unauthorized alert sent to cell phones across parts of the country early...
Read More
By infosecbulletin
/ Sunday , June 21 2026
A new open-source cybersecurity tool named CyberSentinel AI v3.0 has come out. It is an important step in self-operated security...
Read More
By infosecbulletin
/ Saturday , June 20 2026
Barracuda gathered industry people in Dhaka on 18 June 2026 for a roundtable talk about cyber resilience. The company shared...
Read More
By infosecbulletin
/ Saturday , June 20 2026
The U.S. Cybersecurity and Infrastructure Security Agency (CISA) asked Fortinet users with FortiGate devices on Thursday to act to protect...
Read More
By infosecbulletin
/ Saturday , June 20 2026
The U.S. Cybersecurity and Infrastructure Security Agency (CISA) has asked federal agencies to protect their systems by Sunday from a...
Read More
By infosecbulletin
/ Saturday , June 20 2026
The Texas Parks and Wildlife Department (TPWD) revealed a data leak at its license system provider. This leak exposed private...
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 !