# One tampered ChatGPT link could spawn a rogue AI agent that took orders from an attacker every five minutes

> One tampered ChatGPT link could spawn a rogue AI agent that took orders from an attacker every five minutes Key Points - Zenity Labs has revealed a vulnerability in OpenAI's Workspace Agents dubbed "AgentForger," where…

- **Source:** [The-decoder](https://the-decoder.com/one-tampered-chatgpt-link-could-spawn-a-rogue-ai-agent-that-took-orders-from-an-attacker-every-five-minutes/?utm_source=gearopen.com&utm_medium=referral&utm_campaign=feed&utm_content=6a625d2b09947d64cbb6efac)
- **Published:** 2026-07-23
- **Category:** AI & Bots
- **Tags:** #chatgpt #openai #ai
- **Canonical:** http://localhost:4321/a/6a625d2b09947d64cbb6efac

---

_GearOpen's distilled summary. The full original article is published at The-decoder (source link above); GearOpen does not republish the source's full text._