This article examines the security implications of the Model Context Protocol (MCP) sampling feature in the context of a widely used coding copilot application.
MCP is a standard for connecting large language model (LLM) applications to external data sources and tools. We show that, without proper safeguards, malicious MCP servers can exploit the sampling feature for a range of attacks. We demonstrate these risks in practice through three proof-of-concept (PoC) examples conducted within the coding copilot, and discuss strategies for effective prevention.
Read more…
Source: Palo Alto Unit 42
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- Patched WinRAR Bug Still Under Active Attack – Thanks to No Auto-Updates
March 15, 2019
Various cyber criminal groups and individual hackers are still exploiting a recently patched critical code execution vulnerability in WinRAR, a popular Windows file compression application with 500 million users worldwide. Why? Because the WinRAR software doesn’t have an auto-update feature, which, unfortunately, leaves millions of its users vulnerable to cyber attacks. The critical vulnerability (CVE-2018-20250) that was patched ...
- Disrupting the Attack Chain Through Detecting Credential Dumping
March 15, 2019
There are various steps that an attacker must follow in order to execute any successful attack, with the initial compromise being just one stage in the overall attack chain. Once attackers have successfully breached the perimeter of an organization, they enter into the lateral movement phase where they attempt to tiptoe through a network, identifying ...
- IMAP-Based Attacks Compromising Accounts at ‘Unprecedented Scale’
March 14, 2019
That’s according to researchers with Proofpoint, who found that in the past half year, a staggering 60 percent of Microsoft Office 365 and G Suite tenants have been targeted with IMAP-based password-spraying attacks; and 25 percent of those targeted experienced a full-on breach as a result. Password-spraying attacks are when an attacker attempts to access a large ...
- Talking to RATs: Assessing Corporate Risk by Analyzing Remote Access Trojan Infections
March 14, 2019
Remote access trojans (RATs) on a corporate system may serve as a key pivot point to access information laterally within an enterprise network. By analyzing network metadata, Recorded Future analysts were able to identify RAT command-and-control (C2) servers, and more crucially, which corporate networks were communicating to those controllers. This approach allows Recorded Future to ...
- Businesses warned over a new breed of BitLocker attacks
March 14, 2019
Devices protected using Microsoft BitLocker can be physically breached in a new form of attack that involves extracting the encryption keys from a computer’s Trusted Platform Module (TPM) chip. By hardwiring equipment into a computer’s motherboard, namely the TPM chip, attackers would be primed to access any sensitive corporate information stored on encrypted hard drives. This ...
- The fourth horseman: CVE-2019-0797 vulnerability
March 13, 2019
The new zero-day in the Windows OS exploited in targeted attacks In February 2019, our Automatic Exploit Prevention (AEP) systems detected an attempt to exploit a vulnerability in the Microsoft Windows operating system. Further analysis of this event led to us discovering a zero-day vulnerability in win32k.sys. We reported it to Microsoft on February 22, 2019. ...