System Instruction Keywords
Sub-technique of AML.T0069 Discover LLM System Information
Description
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.
- ATLAS ID
- AML.T0069.001
- Maturity
- DemonstratedShown to work in research or red-team exercises.
- Platforms
- Generative AIAgentic AI
Mitigations
- AML.M0005Control Access to AI Models and Data at Rest
Restrict access to stored system instructions and tool definitions containing privileged keywords.
- AML.M0020Generative AI Guardrails
Filter responses that reveal system keywords, tool names, function definitions, or hidden instructions.