Direct Prompt Injection

T1699

Technique.View on attack.mitre.org

About this technique

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.

Detection rules0

Rules on DetectionCode tagged with T1699.

Sigma0

No Sigma rules are mapped to this technique yet.

Splunk0

No Splunk rules are mapped to this technique yet.

Groups0

None recorded.

Software0

None recorded.

Campaigns2

Procedure examples2

Campaigns2

Used byProcedure example
CampaignAI-Assisted Breach of Mexico's Government Infrastructure

During the AI-Assisted Breach of Mexico's Government Infrastructure, the adversary abused Claude Code by utilizing a file-write operation within the prompt that created a `claude.md` file that contained a pre-written 1,084-line document containing penetration testing scripts that were used in the campaign.

CampaignAnthropic AI-orchestrated Campaign

During the Anthropic AI-orchestrated Campaign, the adversary entered a prompt that claimed the user was an employee of a cybersecurity firm and that Claude was being used for defensive cybersecurity testing to authorize restricted operations.

References5

  1. Cybersec Guru Prompt Injection Open source
    The CyberSec Guru. (2026, June 7). The Meta AI exploit: how a prompt injection flaw bypassed 2FA to steal million-dollar Instagram accounts. Retrieved September 18, 2026.
  2. Gemini AI Misuse Jan 2025 Open source
    Google Threat Intelligence Group. (2025, January). Adversarial Misuse of Generative AI. Retrieved September 18, 2026.
  3. NIST Direct Prompt Injection Open source
    NIST. (n.d.). direct prompt injection. Retrieved September 18, 2026.
  4. OWASP Prompt Injection Open source
    OWASP. (n.d.). LLM01:2025 Prompt Injection. Retrieved September 18, 2026.
  5. Palo Alto Prompt Injection Open source
    Palo Alto Networks. (n.d.). What Is a Prompt Injection Attack? [Examples & Prevention]. Retrieved September 18, 2026.

Data from MITRE ATT&CK® (Enterprise). ATT&CK® is a registered trademark of The MITRE Corporation.