Critical out-of-bounds read in Ollama before 0.17.1 leaks process memory including API keys from over 300000 servers via ...

Hugging Face hosts 352,000 unsafe model issues. ClawHub's registry contains 341 malicious AI agent skills. The AI supply chain is now the most attractive target in software security.

New research exposes how prompt injection in AI agent frameworks can lead to remote code execution. Learn how these ...

Malicious repositories can trigger code execution in Claude Code, Cursor CLI, Gemini CLI, and CoPilot CLI with minimal or no ...

The company has this month announced the open source release of BlueRock MCP Python Hooks, a lightweight (software using ...

CVE-2026-22679 exploited via debug endpoint in Weaver E-cology before 20260312, enabling RCE and system compromise.

OX Security confirmed arbitrary command execution on six live platforms and estimates 200,000 MCP servers are exposed. Here's ...

Mistral AI launches Workflows, a Temporal-powered orchestration platform for enterprise AI that automates mission-critical ...

An upcoming execution in Texas has gained the attention of prominent rappers like Travis Scott and T.I. for the questions it raises about the place rap lyrics have in the courtroom and how justice is ...

A Florida man is scheduled for execution next month after his conviction in the killing of his cousin's girlfriend and her 4-year-old daughter under a death warrant signed by Gov. Ron DeSantis ...

The Ruby vulnerability is not easy to exploit, but allows an attacker to read sensitive data, start code, and install backdoors.

A design choice in the MCP SDKs allows remote code execution across the AI supply chain.