Malicious MCP Servers Can Split Instructions to Make AI Coding Agents Exfiltrate Secrets
Researchers at ASSET Research Group have disclosed a new attack technique, dubbed GhostSplice, that exploits the Model Context Protocol (MCP) to trick…
Tag: MCP
ASSET Research Group Discloses GhostSplice MCP Attack
ASSET Research Group, a security research lab, disclosed the GhostSplice technique that exploits MCP to split malicious instructions across channels, tricking AI…
Terraform MCP Server: Critical Vulnerabilities Fixed in Version 1.1.0
HashiCorp's Terraform MCP Server, which connects AI assistants to Terraform over the Model Context Protocol, had three vulnerabilities in its Streamable HTTP…
Ruflo: Open-Source AI Multi-Agent Orchestration Platform Hit by Critical Flaw
Ruflo is an open-source AI agent meta-harness for Anthropic Claude Code and OpenAI Codex. A critical vulnerability (CVE-2026-59726) in versions before 3.16.3…
Critical Ruflo MCP Flaw Allows Unauthenticated Remote Code Execution and AI Memory Poisoning
Cybersecurity researchers have disclosed a maximum-severity vulnerability in Ruflo, an open-source AI multi-agent orchestration platform, that could allow unauthenticated attackers to achieve…
CVE-2026-59726: Critical Ruflo MCP Flaw Allows Unauthenticated RCE and AI Memory Poisoning
CVE-2026-59726 is a maximum-severity vulnerability (CVSS 10.0) in Ruflo, an open-source AI multi-agent orchestration platform. It allows unauthenticated attackers to achieve remote…
FakeGit Campaign Uses 7,600 GitHub Repositories to Spread SmartLoader Malware
Cybersecurity researchers have uncovered a large-scale campaign dubbed FakeGit, which leverages nearly 7,600 malicious GitHub repositories to distribute the SmartLoader malware. The…
NadMesh Botnet Targets Exposed AI Services for Cloud Credentials and Kubernetes Tokens
A new Go-based botnet named NadMesh has been discovered actively hunting exposed AI services to steal cloud credentials and Kubernetes tokens. First…
SASE Has an AI Blind Spot: Why Packet Inspection Falls Short in Modern Enterprise Security
For years, routing traffic through cloud proxies was sufficient for enterprise security. However, the shift to browser-based work, SaaS applications, and generative…
Pentera MCP Server: Integrating Validation into AI Workflows
The Pentera MCP (Model Context Protocol) Server makes Pentera validation data available directly to MCP-compatible AI assistants. It runs locally as a…