New Prompt Injection Attack Vectors Through MCP Sampling


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:

  • Microsoft’s open source tools were hacked to steal passwords of AI developers

    June 8, 2026

    Microsoft has cut off access to dozens of its open source projects hosted on GitHub as it investigates how hackers apparently breached the projects and injected password-stealing malware into the code. Many of the affected projects relate to Microsoft’s cloud service Azure and other tools used by developers to code with AI development apps, such as ...

  • Seeking Counsel: Ongoing Targeted Campaign Against US Law Firms

    June 5, 2026

    From January through May 2026, Mandiant identified a financially motivated data theft extortion campaign executed by the threat cluster UNC3753 (also tracked as “Luna Moth,” “Chatty Spider,” and “Silent Ransom Group”) targeting dozens of organizations across professional, legal, and financial services in the United States. UNC3753 leverages voice phishing (vishing) and social engineering deception techniques to ...

  • Meta, Starlink and Microsoft team up with the FBI to delete over 1.4 million accounts and seize millions in cryptocurrency related to huge scam networks targeting Americans

    June 4, 2026

    Dozens of people have been arrested, and millions of dollars in cryptocurrency seized, in a large-scale, multi-national operation against internet scammers and fraudsters. On May 18, the US Department of Justice, the FBI, Secret Service, law enforcement agencies in the UK, Australia, Canada, New Zealand, and Thailand, as well as multiple commercial businesses such as Meta, ...

  • You do surprise me.exe: An unexpected executable in Hola Browser

    June 4, 2026

    During review work related to an AppEsteem Windows Certified Application test, Sophos X-Ops recently identified an unexpected executable delivered alongside Hola Browser (version 1.251.91.0). The executable, me.exe, was not listed as a certified component, and appears to be a crypto-miner. After the issue was reported through the certification program, Hola reported that they had fixed their delivery pipeline, removing the condition that ...

  • Chinese spies use LinkedIn to target UK officials and military staff

    June 3, 2026

    Chinese spies are targeting UK government and military staff on job websites including LinkedIn to try to get access to classified or sensitive information, MI5 has warned. A bulletin has been released by the Five Eyes powers – the UK, US, Australia, Canada and New Zealand – highlighting an “aggressive” online recruitment strategy where spies for Beijing military ...

  • MiniPlasma: detecting exploitation of a critical unpatched Windows vulnerability

    June 3, 2026

    Over the past two months, the anonymous researcher Nightmare Eclipse (also known as Chaotic Eclipse) has publicly released six Windows vulnerabilities complete with ready-to-use exploits, without prior coordination with Microsoft. The most critical of these is MiniPlasma, a zero-day local privilege escalation exploit that grants attackers SYSTEM-level access. Read more… Source:  Kaspersky Sign up for the Cyber Security ...