Discover LLM System Information
Description
The adversary is trying to discover something about the large language model's (LLM) system information. This may be found in a configuration file containing the system instructions or extracted via interactions with the LLM. The desired information may include the full system prompt, special characters that have significance to the LLM or keywords indicating functionality available to the LLM. Information about how the LLM is instructed can be used by the adversary to understand the system's capabilities and to aid them in crafting malicious prompts.
- ATLAS ID
- AML.T0069
- Maturity
- DemonstratedShown to work in research or red-team exercises.
- Platforms
- Generative AIAgentic AI
Sub-techniques
Mitigations
- AML.M0000Limit Public Release of Information
Withhold public prompt templates, model configuration, and architecture details that could aid LLM reconnaissance.
- AML.M0005Control Access to AI Models and Data at Rest
Restrict access to stored system prompts, configuration files, and model metadata.
- AML.M0019Control Access to AI Models and Data in Production
Authenticate and monitor access to production models and configuration interfaces.
- AML.M0020Generative AI Guardrails
Block output of system prompts, hidden instructions, secrets, and internal configuration details.
Case studies that use it
No ATLAS case study records this technique yet. Browse all case studies.