Posts tagged with: ai security
-
Vibe Coding Is Shipping Vulnerabilities to Production. Here's the Data.
91.5% of vibe-coded apps had at least one vulnerability in Q1 2026. Real incidents — Moltbook, Lovable, Orchids — show what happens when AI-generated code ships without security review. Policy-as-code defenses that actually stop it.
-
MCP Security in 2026: Real CVEs, Exploit Chains, and Policy-as-Code Defenses for AI Tool Infrastructure
A technical analysis of Model Context Protocol (MCP) security vulnerabilities including CVE-2025-6514 (CVSS 9.6), the Anthropic mcp-server-git RCE chain, and real supply chain incidents. Learn the four MCP threat layers and implement policy-as-code defenses with OPA and Falco.