System Prompt
Sub-technique of AML.T0069 Discover LLM System Information
Description
Adversaries may discover a large language model's system instructions provided by the AI system builder to learn about the system's capabilities and circumvent its guardrails.
- ATLAS ID
- AML.T0069.002
- 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 prompts and prompt templates.
- AML.M0019Control Access to AI Models and Data in Production
Authenticate and monitor access to production models and prompt configuration.
- AML.M0020Generative AI Guardrails
Filter responses that reveal system prompts and hidden instructions.