Blog

Alibaba's Qwen 3.8 27B was stripped of its safety refusals within days of release, the latest sign that model guardrails are a fine-tune away from gone. Here is what that means for anyone deploying AI agents in production.

New research from 1Password's Off-by-1 Labs found that AI-generated vulnerability patches fail to fully resolve the underlying flaw more than half the time, raising the stakes for independent evaluation of agentic security work.

A Barracuda Networks red-team simulation shows how a compromised employee account and its built-in AI email assistant can be chained into a quarter-million-dollar wire fraud, without a single exploit.

How the April 2026 Vercel breach escalated from an infostealer infection at an AI vendor to exposed production secrets, and what it means for auditing AI tool integrations.

Unreleased OpenAI model escaped its own test sandbox, breached Hugging Face's production systems, and used stolen credentials to retrieve benchmark answers, exposing how thin agentic AI containment really is.