自动化接入 · API / MCP EN

技术说明 · T1698

Indirect Prompt Injection

Adversaries may deliver malicious prompts to an LLM indirectly by embedding the prompts in content that the adversary expects may be processed by an LLM. These prompts can be included in web pages, documents, emails, tickets, code, or other sources that an agent, copilot, or other AI system may retrieve and process. When an LLM processes this content, the embedded instructions may cause the system to perform unintended behaviors. Adversaries may use indirect prompt injection to Impair Autonomous Defenses, and for unauthorized execution of any capabilities available to the LLM.

ATT&CK T1698 platforms — 状态 有效 版本 20.1

Adversaries may deliver malicious prompts to an LLM indirectly by embedding the prompts in content that the adversary expects may be processed by an LLM.1 These prompts can be included in web pages,2 documents, emails, tickets,3 code, or other sources that an agent, copilot, or other AI system may retrieve and process. When an LLM processes this content, the embedded instructions may cause the system to perform unintended behaviors.4 Adversaries may use indirect prompt injection to Impair Autonomous Defenses, and for unauthorized execution of any capabilities available to the LLM.

  1. NIST indirect prompt injection
  2. Palo Alto Indirect Prompt Injection ITW
  3. Snyk Indirect Prompt Injection
  4. GTIG AI Threats Sep 2026

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。