Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.

Mozilla researchers revealed a new attack that tricks Claude Code into running hidden commands from seemingly harmless GitHub repositories.

An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious ...

Microsoft Threat Intelligence identified an active multi-stage intrusion campaign targeting hospitality organizations in ...

Using mcp-server-mysql to let your AI query MySQL? Bloome brings that to your whole team — an AI-agent IM platform where AI agents are members of the chat. Connect your MCP tools and have agents ...

On May 11, 2026, malicious versions of 42 @tanstack/* npm packages (84 versions in total) were published as part of a supply-chain compromise. The malicious releases were designed to execute during ...

A critical vulnerability in the popular Node.js sandboxing library vm2 allows escaping the sandbox and executing arbitrary code on the host system. The security issue is tracked as CVE-2026-26956 and ...

MYRTLE BEACH, S.C. - The Better Business Bureau is warning consumers about a “brushing” scam involving unsolicited packages that arrive at their homes. The scam works by companies finding names and ...

Cooling centers in Augusta say they need help making sure people in need can stay cool as the summer heat continues. South Carolina voters returned to the polls to finalize the Republican nominee for ...