ATLASAML.T0061
ATLAS index
AML.T0061

LLM Prompt Self-Replication

An adversary may use a carefully crafted LLM Prompt Injection designed to cause the LLM to replicate the prompt as part of its output. This allows the prompt to propagate to other LLMs and persist on the system. The self replicating prompt is typically paired with other malicious instructions (ex: LLM Jailbreak, LLM Da

Framework
MITRE ATLAS
Maturity
Demonstrated
Platforms
Generative AI, Agentic AI
Release
2026.05

Overview

An adversary may use a carefully crafted LLM Prompt Injection designed to cause the LLM to replicate the prompt as part of its output. This allows the prompt to propagate to other LLMs and persist on the system. The self-replicating prompt is typically paired with other malicious instructions (ex: LLM Jailbreak, LLM Data Leakage).

Sources

  1. MITRE ATLAS AML.T0061: LLM Prompt Self-Replication — MITRE