CVE-2026-5752 CVSS 9.3 flaw in Terrarium enables root code execution via Pyodide prototype traversal, risking container ...

CVE-2026-5760 (CVSS 9.8) exposes SGLang via /v1/rerank endpoint, enabling RCE through malicious GGUF models, risking server ...

The CVSS‑9.3 vulnerability allows unauthenticated remote code execution on exposed Marimo servers and was exploited in the wild shortly after disclosure, Sysdig says.

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

Unsafe defaults in MCP configurations open servers to possible remote code execution, according to security researchers who ...

An unpatched vulnerability in Anthropic's Model Context Protocol creates a channel for attackers, forcing banks to manage the ...

A design flaw – or expected behavior based on a bad design choice, depending on who is telling the story – baked into ...

Tencent Cloud's Cube Sandbox goes fully open source with five technical breakthroughs, providing a production-grade foundation for AI Agent deployment at industrial scale.

However, in a report published on April 15, researchers at Ox Security claimed that a flaw in the protocol could enable ...

Anthropic’s Model Context Protocol, a fast-growing standard used to connect AI models with external tools and data, has come ...

VectorCertain LLC today announced new validation results demonstrating that its SecureAgent platform successfully detected ...

This week in cybersecurity: 338 new CVEs published including 11 critical severity. 9 vulnerabilities added to CISA KEV catalog. Plus major developments in AI security, supply chain attacks, and ...