Execution

T1699: Direct Prompt Injection

Adversaries may input malicious prompts directly into an LLM’s user interface.(Citation: NIST Direct Prompt Injection) The prompts can be designed to bypass safeguards, manipulate context, override pr...

T1699 · Technique ·2 platforms

Description

Adversaries may input malicious prompts directly into an LLM’s user interface.(Citation: NIST Direct Prompt Injection) The prompts can be designed to bypass safeguards, manipulate context, override previous instructions, or coerce the LLM into unauthorized behavior.(Citation: OWASP Prompt Injection)

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.(Citation: Gemini AI Misuse Jan 2025)(Citation: Palo Alto Prompt Injection) 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.(Citation: Cybersec Guru Prompt Injection)

Platforms

WindowsSaaS

Mitigations (4)

User Account ManagementM1018

Associate AI interactions with authenticated identities and constrain AI-mediated actions to the permissions of the initiating user. Do not allow prompt content to establish or elevate the authorization context used by downstream tools or services.

Execution PreventionM1038

Prevent user-supplied AI prompts from directly authorizing consequential actions. Enforce tool, API, command, and resource authorization outside the model and reject requested actions that exceed the permissions associated with the initiating user or agent task.

User TrainingM1017

Train users responsible for AI-enabled systems to recognize attempts to manipulate system instructions, role boundaries, or safety controls through user-provided prompts and to independently validate consequential AI-generated actions.

Privileged Account ManagementM1026

Restrict access to privileged AI capabilities and require explicit authorization or human approval for AI-generated actions involving administrative functions, sensitive resources, or privileged tools.

References

Frequently Asked Questions

What is T1699 (Direct Prompt Injection)?

T1699 is a MITRE ATT&CK technique named 'Direct Prompt Injection'. It belongs to the Execution tactic(s). Adversaries may input malicious prompts directly into an LLM’s user interface.(Citation: NIST Direct Prompt Injection) The prompts can be designed to bypass safeguards, manipulate context, override pr...

How can T1699 be detected?

Detection of T1699 (Direct Prompt Injection) typically involves monitoring system logs, network traffic, and endpoint telemetry. Use SIEM rules, EDR solutions, and behavioral analytics to identify suspicious activity associated with this technique.

What mitigations exist for T1699?

There are 4 documented mitigations for T1699. Key mitigations include: User Account Management, Execution Prevention, User Training, Privileged Account Management.

Which threat groups use T1699?

While specific threat group attribution may vary, this technique has been observed in various real-world attacks. Check the MITRE ATT&CK website for the latest threat intelligence.