自动化接入 · API / MCP EN

技术说明 · T1700

AI-Enabled Exfiltration

Adversaries may utilize Direct Prompt Injection, Indirect Prompt Injection or other methods to instruct enterprise AI agents to exfiltrate data. When enterprise systems incorporate the use of AI assistants or other AI agents, adversaries may abuse these systems to weaponize sanctioned tools available to the agent. As an AI agent processes queries or ingests data, an injected prompt can cause the agent to use its tool connections in unauthorized or unintended ways. When AI agents are induced to exfiltrate data, other exfiltration techniques likely apply as well to transfer the information out of the network, such as Exfiltration to Code Repository or Exfiltration Over Web Service.

ATT&CK T1700 platforms — 状态 有效 版本 20.1

Adversaries may utilize Direct Prompt Injection, Indirect Prompt Injection or other methods to instruct enterprise AI agents to exfiltrate data.12 When enterprise systems incorporate the use of AI assistants or other AI agents, adversaries may abuse these systems to weaponize sanctioned tools available to the agent.3 As an AI agent processes queries or ingests data, an injected prompt can cause the agent to use its tool connections in unauthorized or unintended ways. When AI agents are induced to exfiltrate data, other exfiltration techniques likely apply as well to transfer the information out of the network, such as Exfiltration to Code Repository or Exfiltration Over Web Service.45

  1. Prompt-Injection Exfil
  2. Anthropic Report Sep 2026
  3. Google Security State of Prompt Injections
  4. Google Cloud AI Risk Sep 2026
  5. Barracuda Prompt Injection Phishing Emails

使用该技术的组织

参考表中尚无组织使用记录。

断言

尚无指向该技术的公开断言。

记录自动入库·未人工复核；置信度与有效期按引用读取。