Threat intelligence / Technique

Discover LLM System Information

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.

Technique

TypeTechnique

External ID—

First seen2026-08-14

Last seen2026-08-14

Confidence

—

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.

7 recorded

Relationships

mitigates

from Control Access to AI Models and Data at Rest

Mitigation

mitigates

from Control Access to AI Models and Data in Production

Mitigation

mitigates

from Generative AI Guardrails

Mitigation

mitigates

from Limit Public Release of Information

Mitigation

subtechnique-of

from Special Character Sets

Technique

subtechnique-of

from System Instruction Keywords

Technique

subtechnique-of

from System Prompt

Technique

1 external

References

mitre-atlas

AML.T0069