# A single prompt was enough to hijack every AI agent in an AWS account, Zenity researchers found

> 全文为英语

**Published:** 2026年10月8日
**Author:** Jonathan Kemper
**Source:** The Decoder
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/a-single-prompt-was-enough-to-hijack-every-ai-agent-in-an-aws-account-ze

Zenity Labs researchers say a single publicly accessible AI agent on Amazon's Bedrock AgentCore was enough to take over every AgentCore agent in the same AWS account and region. The attack exploited an internal AWS interface for temporary cloud credentials that agents could…

> 内容来自原始来源： **The Decoder**
> [在 The Decoder 阅读全文](https://the-decoder.com/a-single-prompt-was-enough-to-hijack-every-ai-agent-in-an-aws-account-zenity-researchers-found/)

---

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