AML.T0069.001 sub-technique demonstrated
System Instruction Keywords
Sub-technique of AML.T0069 — Discover LLM System Information
Adversaries may discover keywords that have special meaning to the large language model (LLM), such as function names or object names. These can later be exploited to confuse or manipulate the LLM into misbehaving and to make calls to plugins the LLM has access to.
> curated attacks (0)
No curated attacks mapped to this technique yet.