485 matches found
LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems
Large Language Model LLM-based agents have demonstrated remarkable capabilities in reasoning, planning, and tool usage. The recently proposed Model Context Protocol MCP has emerged as a unifying framework for integrating external tools into agent systems, enabling a thriving open ecosystem of...
MCP Watch 操作系统命令注入漏洞
MCP Watch is a comprehensive security scanning program for Model Context Protocol servers by the individual developer Kapil Duraphe. An operating system command injection vulnerability exists in MCP Watch version 0.1.2 and earlier, which stems from command injection and could lead to arbitrary...
PT-2025-48575
Name of the Vulnerable Software and Affected Versions MCP Watch versions 0.1.2 and earlier Description MCP Watch, a security scanner for Model Context Protocol MCP servers, contains a Command Injection issue in the cloneRepo method of the MCPScanner class. The application directly passes the...
Hiding in the AI Traffic: Abusing MCP for LLM-Powered Agentic Red Teaming
Generative AI is reshaping offensive cybersecurity by enabling autonomous red team agents that can plan, execute, and adapt during penetration tests. However, existing approaches face trade-offs between generality and specialization, and practical deployments reveal challenges such as...
Chinese Hackers Use Anthropic's AI to Launch Automated Cyber Espionage Campaign
State-sponsored threat actors from China used artificial intelligence AI technology developed by Anthropic to orchestrate automated cyber attacks as part of a "highly sophisticated espionage campaign" in mid-September 2025. "The attackers used AI's 'agentic' capabilities to an unprecedented degre...
INTERN(al) MSRC variant hunting: From multi-tenant authorization to Model Context Protocol
When security researchers submit a vulnerability report to MSRC, the Vulnerabilities and Mitigations V&M team reviews it, reproduces the issue, and determines severity. The team reviews all submissions from internal and external security researchers...
AI Explainer: What Is Model Context Protocol?
...
CVE-2025-64109
Cursor is a code editor built for programming with AI. In versions and below, a vulnerability in the Cursor CLI Beta allowed an attacker to achieve remote code execution through the MCP Model Context Protocol server mechanism by uploading a malicious MCP configuration in .cursor/mcp.json file in ...
CVE-2025-64109 Cursor CLI Beta: Command Injection via Untrusted MCP Configuration
Cursor is a code editor built for programming with AI. In versions and below, a vulnerability in the Cursor CLI Beta allowed an attacker to achieve remote code execution through the MCP Model Context Protocol server mechanism by uploading a malicious MCP configuration in .cursor/mcp.json file in ...
CVE-2025-64109 Cursor CLI Beta: Command Injection via Untrusted MCP Configuration
Cursor is a code editor built for programming with AI. In versions and below, a vulnerability in the Cursor CLI Beta allowed an attacker to achieve remote code execution through the MCP Model Context Protocol server mechanism by uploading a malicious MCP configuration in .cursor/mcp.json file in ...
PT-2025-45063
Name of the Vulnerable Software and Affected Versions Cursor versions prior to 2025.09.17-25b418f Description Cursor is a code editor designed for programming with AI. A flaw in the Cursor CLI Beta could allow a remote attacker to execute code. This is possible through the Model Context Protocol...
When APIs Become Attack Paths: What the Q3 2025 ThreatStats Report Tells Us
Wallarm’s latest Q3 2025 API ThreatStats report link placeholder reveals that API vulnerabilities, exploits, and breaches are not just increasing; they’re evolving. Malicious actors are shifting from code-level weaknesses to business logic flaws, from web apps to partner integrations, and from RE...
MCPGuard : Automatically Detecting Vulnerabilities in MCP Servers
The Model Context Protocol MCP has emerged as a standardized interface enabling seamless integration between Large Language Models LLMs and external data sources and tools. While MCP significantly reduces development complexity and enhances agent capabilities, its openness and extensibility...
Securing AI Agent Execution
Large Language Models LLMs have evolved into AI agents that interact with external tools and environments to perform complex tasks. The Model Context Protocol MCP has become the de facto standard for connecting agents with such resources, but security has lagged behind: thousands of MCP servers...
oatpp-mcp 安全特征问题漏洞
oatpp-mcp is an Oat++ open source implementation of the Model Context Protocol. A security signature issue vulnerability exists in oatpp-mcp that stems from an MCP SSE endpoint returning an instance pointer as a session ID, which could lead to a session hijacking attack...
Toward Understanding Security Issues in the Model Context Protocol Ecosystem
The Model Context Protocol MCP is an emerging open standard that enables AI-powered applications to interact with external tools through structured metadata. A rapidly growing ecosystem has formed around MCP, including a wide range of MCP hosts i.e., Cursor, Windsurf, Claude Desktop, and Cline, M...
Severe Framelink Figma MCP Vulnerability Lets Hackers Execute Code Remotely
Cybersecurity researchers have disclosed details of a now-patched vulnerability in the popular figma-developer-mcp Model Context Protocol MCP server that could allow attackers to achieve code execution. The vulnerability, tracked as CVE-2025-53967 CVSS score: 7.5, is a command injection bug...
Another Critical RCE Discovered in a Popular MCP Server
Artificial Intelligence development is moving faster than secure coding practices, and attackers are taking notice. Imperva Threat Research recently uncovered and disclosed a critical Remote Code Execution RCE vulnerability CVE-2025-53967 in the Framelink Figma MCP Server. This is just one exampl...
