Affected Technology

Tool Poisoning incidents

Malicious tool and connector manipulation

Matching incidents

3

Technology type

Topic

Low severity STABLE

Meta Prompt Injection Vulnerability

Architectural vulnerabilities within Large Language Model (LLM) environments integrated with the Model Context Protocol (MCP) enable attackers to embed malicious instructions within data content or tool metadata. This flaw allows for indirect prompt injection and tool poisoning, compelling LLMs to autonomously perform unauthorized actions such as data exfiltration or triggering enterprise workflows.

MetaMCPPrompt InjectionTool PoisoningAI ConundrumBe Patched Away
1 source: darkreading.com Updated 5mo ago
Low severity STABLE

AI Privilege Escalation Vulnerability

NSFOCUS has identified emerging threats targeting AI Agents and Large Language Models (LLMs), specifically through sophisticated attacks leveraging Multi-Agent Communication Protocols (MCPs) to achieve unauthorized access, privilege escalation, and intent manipulation. These new vulnerabilities include "MCP Tool Poisoning Attacks" and "Intent Disruption & Goal Manipulation," which could lead to system intrusion, data tampering, and the spread of erroneous information across multi-agent systems.

AI AgentsMCPTool PoisoningAI LLM RiskGovernanceNSFOCUS Unveils Enhanced
Low severity STABLE

AI Supply-Chain Compromise

The adoption of Model Context Protocol (MCP) exposes AI agent supply chains to critical vulnerabilities, specifically "tool poisoning attacks" where malicious instructions are embedded to exfiltrate data or alter workflows, and "rug pull attacks" involving weaponized tool updates. Cisco's open-source MCP Scanner is designed to detect these malicious code, over-privileged permissions, and hidden threats within MCP servers, thereby securing agentic AI deployments against such exploits.

1 source: blogs.cisco.com Updated 10mo ago

Back to intelligence feed