TechniquediscoveryATLAS

AML.T0069Discover LLM System Information

What it is

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.

References

  1. https://atlas.mitre.org/techniques/AML.T0069

Related by meaning· 6

Nearest entities by semantic similarity across the cs-graph corpus.

ATLAS
Extract LLM System Prompt
ATLAS
Discover AI Agent Configuration
ATLAS
LLM Prompt Crafting
ATLAS
Discover AI Artifacts
ATLAS
LLM Data Leakage
ATLAS
Discover LLM Hallucinations
Sourced from MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Curated by Adam Lundqvist, SQUR.