Indirect Prompt Injection

T1698

Technique.View on attack.mitre.org

About this technique

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.

Detection rules0

Rules on DetectionCode tagged with T1698.

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.

Campaigns0

None recorded.

Procedure examples0

No procedure examples are recorded for this technique.

References4

  1. GTIG AI Threats Sep 2026 Open source
    Google Threat Intelligence Group. (2026, September 8). GTIG AI Threat Tracker: From Prompting to Autonomy – The Evolution of Adversarial AI. Retrieved September 18, 2026.
  2. NIST indirect prompt injection Open source
    NIST. (n.d.). indirect prompt injection. Retrieved September 18, 2026.
  3. Palo Alto Indirect Prompt Injection ITW Open source
    Beliz Kaleli Shehroze Farooqi Oleksii Starov Nabeel Mohamed. (2026, March 3). Fooling AI Agents: Web-Based Indirect Prompt Injection Observed in the Wild. Retrieved September 18, 2026.
  4. Snyk Indirect Prompt Injection Open source
    Stephen Thoemmes. (2026, February 19). How “Clinejection” Turned an AI Bot into a Supply Chain Attack. Retrieved September 18, 2026.

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