TechniquepersistenceATLAS
AML.T0061LLM Prompt Self-Replication
What it is
An adversary may use a carefully crafted [LLM Prompt Injection](/techniques/AML.T0051) 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](/techniques/AML.T0054), [LLM Data Leakage](/techniques/AML.T0057)).
References
Related by meaning· 6
Nearest entities by semantic similarity across the cs-graph corpus.