Automation · API / MCP 中文

Technique note · T1685.007

Impair Autonomous Defenses

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. 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. 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.

ATT&CK T1685.007 platforms — Status Active Version 20.1

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.1 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.23 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.4

  1. Prompt Injection LLM-Powered SOC Assistants
  2. MacOS.Gaslight Prompt Injection
  3. Gaslight AI triage prompt injection
  4. Shai-Hulud May 2026

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.