Microsoft Incident Response has detailed a new attack pattern targeting AI agents that use Model Context Protocol (MCP) tools, where attackers poison tool metadata to manipulate agent actions. The tec…
AI-powered systems in production face critical security vulnerabilities, including prompt injection and tool-based exploits, as demonstrated by real-world incidents in 2025 such as a Supabase agent da…
Microsoft researchers propose using information-flow control (IFC) to secure autonomous AI agents against prompt injection and data exfiltration. IFC labels data with integrity and confidentiality tag…
The Model Context Protocol (MCP) is becoming the standard API for LLMs, but security vulnerabilities like path traversal and broken tenant isolation are emerging. To prevent damage from autonomous age…
A developer built ghostprobe, a red-team scanner for MCP servers that detects tool poisoning and the 'lethal trifecta' of data access, sink, and untrusted input. When pointed at real servers, it found…
The NSA’s Model Context Protocol (MCP) security guidance and the OWASP MCP Top 10 risk framework can be mapped together to create a testable checklist for vetting MCP servers before deployment. Resear…
Snyk's agent-scan tool analyzes MCP servers by actually executing them from the user's configuration files, retrieving tool descriptions via the MCP protocol, and sending that data to a third-party AP…