In this article, Kaspersky researchers explore how the Model Context Protocol (MCP) — the new “plug-in bus” for AI assistants — can be weaponized as a supply chain foothold.
The researchers start with a primer on MCP, map out protocol-level and supply chain attack paths, then walk through a hands-on proof of concept: a seemingly legitimate MCP server that harvests sensitive data every time a developer runs a tool. Then they break down the source code to reveal the server’s true intent and provide a set of mitigations for defenders to spot and stop similar threats.
Read more…
Source: Kaspersky
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- CISA: Advanced Persistent Threat Actors Targeting U.S. Think Tanks
December 1, 2020
The Cybersecurity and Infrastructure Security Agency (CISA) and the Federal Bureau of Investigation (FBI) have observed persistent continued cyber intrusions by advanced persistent threat (APT) actors targeting U.S. think tanks. This malicious activity is often, but not exclusively, directed at individuals and organizations that focus on international affairs or national security policy. The following guidance ...
- Dox, steal, reveal. Where does your personal data end up?
December 1, 2020
The technological shift that we have been experiencing for the last few decades is astounding, not least because of its social implications. Every year the online and offline spheres have become more and more connected and are now completely intertwined, leading to online actions having real consequences in the physical realm — both good and ...
- Gootkit malware returns to life alongside REvil ransomware
November 30, 2020
After a year-long vacation, the Gootkit information-stealing Trojan has returned to life alongside REvil Ransomware in a new campaign targeting Germany. The Gootkit Trojan is Javascript-based malware that performs various malicious activities, including remote access for threat actors, keystroke capturing, video recording, email theft, password theft, and the ability to inject malicious scripts to steal online ...
- Digitally Signed Bandook Trojan Reemerges in Global Spy Campaign
November 30, 2020
A wave of targeted cyberattack campaigns bent on espionage is cresting around the globe, using a strain of a 13-year old backdoor trojan named Bandook. According to Check Point Research, Bandook was last spotted being used in 2015 and 2017/2018, in the “Operation Manul” and “Dark Caracal” campaigns, respectively. The malware then all but disappeared from ...
- FINRA Alerts Firms to Phishing Email Using Invest-FINRA.org Domain Name
November 30, 2020
FINRA warns member firms of an ongoing phishing campaign that involves fraudulent emails that include the domain “@invest-finra.org”. FINRA recommends that anyone who clicked on any link or image in the email immediately notify the appropriate individuals in their firm of the incident. The domain of “invest-finra.org” is not connected to FINRA and firms should delete ...
- A hacker is selling access to the email accounts of hundreds of C-level executives
November 30, 2020
A threat actor is currently selling passwords for the email accounts of hundreds of C-level executives at companies across the world. The data is being sold on a closed-access underground forum for Russian-speaking hackers named Exploit.in, ZDNet has learned this week. The threat actor is selling email and password combinations for Office 365 and Microsoft accounts, which ...