# OpenAI agents discussed ways to escape their sandbox on public wiki

**Published:** September 4, 2026
**Author:** Dan Goodin
**Source:** Ars Technica — AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/openai-agents-discussed-ways-to-escape-their-sandbox-on-public-wiki

Self-identifying OpenAI agents posted 18,000 messages to a public wiki that discussed ways for other agents to bypass security sandbox restrictions during what was likely internal testing designed to gauge the agents’ hacking abilities, researchers said Friday. In all, agents…

> From the original source: **Ars Technica — AI**
> [Read full article at Ars Technica — AI](https://arstechnica.com/security/2026/09/openai-agents-discussed-ways-to-escape-their-sandbox-on-public-wiki/)

**Tags:** #OpenAI

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*