A flaw in the OpenCode AI coding agent allowed a malicious or hijacked MCP server to run code on a developer’s Windows or WSL machine when the developer… Continue reading
Tag: MCP
The Hacker NewsOct 06, 2026Supply Chain / Artificial Intelligence In 2024, MCP (Model Context Protocol) set out to become the USB-C of AI: one standard for connecting models,… Continue reading
Swati KhandelwalSep 29, 2026Identity Security / Artificial Intelligence A malicious MCP server could trick an application built on the official MCP Python SDK into handing over the OAuth credentials it… Continue reading
Swati KhandelwalAug 25, 2026Vulnerability / AI Security Marimo has addressed a high-severity security flaw in its notebook software that allowed an attacker to execute an attacker-supplied Model Context… Continue reading
Ravie LakshmananAug 17, 2026Cybersecurity / Hacking The expensive attacks are not always the clever ones. This week had plenty of proof. Exposed services got hit, old bugs found… Continue reading
The Hacker NewsAug 17, 2026AI Security / Identity Security MCP servers can expose enterprise secrets through plaintext configuration files, over-permissioned access and prompt injection, often before security teams… Continue reading
Hacker news
Malicious MCP Servers Can Split Instructions to Make AI Coding Agents Exfiltrate Secrets
Swati KhandelwalAug 11, 2026AI Security / Cyber Attack A malicious tool server connected to an AI coding assistant can quietly walk off with SSH keys, environment secrets, source… Continue reading
Ravie LakshmananAug 10, 2026Cybersecurity / Hacking A lot of security problems still begin with someone doing a completely normal thing. Cloning a repo. Answering a call. Leaving a… Continue reading
HashiCorp, Veeam, and the Django Software Foundation have patched 11 vulnerabilities across Terraform MCP Server, Veeam Service Provider Console, and Django. The three most serious: An unauthenticated flaw… Continue reading
Cybersecurity researchers have flagged a maximum-severity security flaw in Ruflo, an open-source agent meta-harness for Anthropic Claude Code and OpenAI Codex, that could result in unauthenticated remote code… Continue reading
