> ## Content Index
> Fetch the complete content index at: https://adjacent.media/llms.txt
> Use this file to discover other available public pages before exploring further.

# AWS Agent Flaw Exposes Credential Theft Through Simple Prompts
- URL: https://adjacent.media/signals/aws-agent-flaw-exposes-credential-theft-through-simple-prompts/
- Published: 2026-10-11T10:11:43.000Z
- Updated: 2026-10-11T10:11:43.000Z
- Description: Amazon’s AgentCore system was vulnerable to a basic social engineering attack—a malicious prompt could convince the AI agent to hand over AWS credentials stored in its memory, turning a foundation model into an unwitting credential harvester.
- Author: Jonathan Greene
- Tags: #signal, theme-ai, prompt injection, llm security, agent systems

Source: [Theregister](https://www.theregister.com/security/2026/10/09/aws-agentcore-security-undone-by-prompt-requesting-credentials/5302436?ref=adjacent.media)

Amazon's AgentCore system was vulnerable to a basic social engineering attack—a malicious prompt could convince the AI agent to hand over AWS credentials stored in its memory, turning a foundation model into an unwitting credential harvester. AWS shipped agentic tools without basic guardrails against prompt injection. As enterprises deploy autonomous agents with real infrastructure access, the gap between stated security postures and actual threat modeling will widen.