MITRE ATT&CK

Adversaries may use methods like Indirect Prompt Injection to disrupt, disable, or otherwise impair autonomous defensive capabilities such as LLM-assisted processing of malware, artifacts, or activity.(Citation: Prompt Injection LLM-Powered SOC Assistants) This behavior may cause a system to ignore data, fail to alert on malicious activity, abort analysis, or to be disabled completely.

Adversaries may include content in malware implants that mimic an LLM prompt scaffold that contains fake system messages in order to convince the LLM that it has encountered an error.(Citation: MacOS.Gaslight Prompt Injection)(Citation: Gaslight AI triage prompt injection) Depending on the type of error, the LLM may abort analysis, truncate, or refuse to continue. Adversaries may also embed prompts in malware intended to stop agents or systems from analyzing the malware.(Citation: Shai-Hulud May 2026)