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:
- Ex-spymaster and fellow Brexiteers’ emails leaked by suspected Russian op
May 26, 2022
Emails between leading pro-Brexit figures in the UK have seemingly been stolen and leaked online by what could be a Kremlin cyberespionage team. The messages feature conversations between former spymaster Richard Dearlove, who led Britain’s foreign intelligence service MI6 from 1999 to 2004; Baroness Gisela Stuart, a member of the House of Lords; and Robert Tombs, ...
- CISA Adds 34 Known Exploited Vulnerabilities to Catalog
May 25, 2022
CISA has added 34 new vulnerabilities to its Known Exploited Vulnerabilities Catalog, based on evidence of active exploitation. These types of vulnerabilities are a frequent attack vector for malicious cyber actors and pose significant risk to the federal enterprise. Note: to view the newly added vulnerabilities in the catalog, click on the arrow on the of ...
- What’s wrong with automotive mobile apps?
May 25, 2022
The recent story about the 19-year-old hacker who took control of several dozen Tesla cars has become something of a sensation. We already know that there was an issue with a third-party app that enabled access to data from Teslas. This made it possible for the security researcher to lock and unlock the cars, turn the ...
- New Linux-Based Ransomware Cheerscrypt Targets ESXi Devices
May 25, 2022
Tremd Micro researchers recently observed multiple Linux-based ransomware detections that malicious actors launched to target VMware ESXi servers, a bare-metal hypervisor for creating and running several virtual machines (VMs) that share the same hard drive storage. Trend Micro encountered Cheerscrypt, a new ransomware family, that has been targeting a customer’s ESXi server used to manage ...
- Fake Windows exploits target infosec community with Cobalt Strike
May 24, 2022
A threat actor targeted security researchers with fake Windows proof-of-concept exploits that infected devices with the Cobalt Strike backdoor. Whoever is behind these attacks took advantage of recently patched Windows remote code execution vulnerabilities tracked as CVE-2022-24500 and CVE-2022-26809. When Microsoft patches a vulnerability, it is common for security researchers to analyze the fix and release proof-of-concept ...
- Anatomy of a DDoS amplification attack
May 23, 2022
Amplification attacks are one of the most common distributed denial of service (DDoS) attack vectors. These attacks are typically categorized as flooding or volumetric attacks, where the attacker succeeds in generating more traffic than the target can process, resulting in exhausting its resources due to the amount of traffic it receives. In this blog, we start ...