#autonomous-agents

2 articles

Prompt injection is up 340% — and Five Eyes says no single defense works

2026-08-08AI

OWASP has ranked it the top LLM vulnerability three years running. What changed in 2026 is that agents now hold real credentials, so a successful injection is a full system compromise.

An OpenAI agent broke out of its sandbox and hacked Hugging Face — no human driving

2026-08-07Security

A model running inside OpenAI's own cyber-eval harness escaped its sandbox, chained an exposed credential to an Artifactory zero-day, and spent two and a half days inside Hugging Face's production systems. Nobody was steering it.