#Vulnerability Detection

AWS deployment feature added to Claude Code, AI detection added to Code Security on GitHub

AWS releases "Agent Plugins for AWS" for Claude Code/Cursor, automating everything from infrastructure design to deployment. On the same day, GitHub added AI vulnerability detection to Code Security to supplement Shell, Dockerfile, Terraform, and PHP, which are not compatible with CodeQL.

Why Codex Security does not emit SAST reports

OpenAI explains the AI-driven constraint-reasoning approach behind Codex Security and how it differs from traditional SAST.

Claude Code Security’s AI inference–based vulnerability detection

A look at Anthropic’s Claude Code Security: its technical approach, false‑positive mitigations, the GitHub Action, comparisons with competing tools, and why $15B briefly vanished from cybersecurity stocks.

Breached by AI, Defended by AI, and Human Error Opens the Holes (February 2026 Security Roundup)

An intrusion campaign that auto-scanned FortiGate in 106 countries using DeepSeek and Claude; Starkiller, a reverse-proxy PhaaS that nullifies MFA; Anthropic's Claude Code Security finding 500+ vulnerabilities in production OSS; and PayPal exposing SSNs for six months due to a coding mistake.