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

> Полный текст доступен на английском

**Published:** 8 октября 2026 г.
**Author:** Jonathan Kemper
**Source:** The Decoder
**Language:** en-US
**HTML:** https://aiqazaqstan.com/ru/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…

> Материал агрегирован из первоисточника: **The Decoder**
> [Читать полностью в The Decoder](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.*