LeituraPesquisaRadarFramework de investimento
Entrar / Cadastrar
← Voltar para a leitura
NotíciasTópico · 蓝鱼AI代理蓝图攻击Material2 min de leituraEditorial DisconfirmAI

Security firm Proofpoint reports 'BluePhishing' scam abusing Microsoft Entra Agent ID blueprints to inject malicious AI agents

Proofpoint found attackers use social engineering to trick users into approving malicious AI agent blueprints, creating up to 250 unauthorized identities in Microsoft corporate environments.

2026-11-11 01:25 GMT+8

Cybersecurity firm Proofpoint has published a report detailing a new attack technique dubbed "BluePhishing." The method exploits Microsoft's Entra Agent ID system by using social engineering to trick enterprise users into approving malicious AI agent blueprints, thereby injecting controlled AI agents into target corporate networks.

Entra Agent ID is an extension of Microsoft Entra that allows organizations to create digital identities for AI agents and manage their access permissions. To simplify deployment, Microsoft introduced "agent blueprints," templates used to batch-create multiple AI agent identities with specific permissions. Proofpoint's research shows that attackers can create a blueprint configured with malicious permissions in their own Microsoft environment and then generate a link pointing to a genuine Microsoft authorization page.

Unlike traditional phishing attacks, this technique does not require spoofing a login page. Attackers only need basic information about the target organization, such as its tenant ID and details of a specific user, to send the link via email or instant messaging. When the victim clicks the link and approves the blueprint in the authentic Microsoft consent popup, the malicious AI agent gains entry to the corporate environment. Once inside, the agent can leverage the AgentIdentity.CreateAsManager permission to clone itself, with a single blueprint capable of generating up to 250 distinct malicious agent identities, each holding tokens with access to internal company resources.

Entrar / Cadastrar
LeituraPesquisaRadarFramework de investimento

Proofpoint recommends that enterprises restrict third-party agent consent, apply least-privilege controls, and monitor audit logs for agent creation events. Since the malicious agent blueprint ID remains consistent across all tenants that grant consent, it serves as an indicator for detecting and removing known malicious agents.

Fontes

  • techradar.comTechRadar↗
Tópico

蓝鱼AI代理蓝图攻击

安全公司Proofpoint披露了一种名为“蓝鱼”(BluePhishing)的新型攻击手法,该手法利用微软Entra Agent ID中的“代理蓝图”功能,通过社会工程学诱导用户批准恶意AI代理,从而在企业环境中创建多达250个未授权身份…

4 etapas1 peçasAtualizado 2026-11-13 22:24

Como chegamos aqui

  1. 2026-11-09美国网络安全公司Proofpoint发布研究报告,首次披露“BluePhishing”攻击手法,指出其针对Microsoft Entra Agent ID的代理蓝图授权流程进行滥用。proofpoint.com ↗
  2. 2026-11-10TechRadar等媒体跟进报道,详细解析攻击链条:攻击者配置恶意蓝图,诱骗受害者点击真实授权链接,获批后自动获得AgentIdentity.CreateAsManager权限,进而批量创建代理身份。techradar.com ↗
  3. 2026-11-11Cybersecurity News进一步分析指出,微软消息中心通知MC1506733显示,自2026年11月起,默认情况下普通Entra用户将能够创建代理蓝图,这扩大了攻击面。cybersecuritynews.com ↗

O que ainda está indefinido

  • 微软是否会在未来版本中修改AgentIdentity.CreateAsManager权限的不可撤销特性或增强蓝图继承权限的可见性?
  • 随着AI代理普及,是否有其他云服务商的身份系统存在类似的“合法授权页+恶意模板”组合攻击风险?
  • 企业如何在不阻碍正常AI代理部署的前提下,有效区分合法的多租户蓝图与潜在的恶意蓝图?
Ler o tópico completo →
Continuar pesquisando →