Automation · API / MCP 中文

Technique note · T1699

Direct Prompt Injection

Adversaries may input malicious prompts directly into an LLM’s user interface. The prompts can be designed to bypass safeguards, manipulate context, override previous instructions, or coerce the LLM into unauthorized behavior. Adversaries may use direct prompt injection to Generate Content prohibited by the LLM's guardrails or to induce the system to utilize its capabilities in unintended or prohibited ways. Adversaries may achieve this by instructing the LLM to ignore previous instructions or safety rules, or by impersonating a role such as a researcher or privileged user.

ATT&CK T1699 platforms — Status Active Version 20.1

Adversaries may input malicious prompts directly into an LLM’s user interface.1 The prompts can be designed to bypass safeguards, manipulate context, override previous instructions, or coerce the LLM into unauthorized behavior.2 Adversaries may use direct prompt injection to Generate Content prohibited by the LLM's guardrails or to induce the system to utilize its capabilities in unintended or prohibited ways.34 Adversaries may achieve this by instructing the LLM to ignore previous instructions or safety rules, or by impersonating a role such as a researcher or privileged user.5

  1. NIST Direct Prompt Injection
  2. OWASP Prompt Injection
  3. Gemini AI Misuse Jan 2025
  4. Palo Alto Prompt Injection
  5. Cybersec Guru Prompt Injection

Groups using this technique

No group use in the reference set yet.

Claims

No public claim points at this technique yet.

Auto-ingested and not human-reviewed; confidence and validity read by citation.