MITRE ATLAS · Discovery
AML.T0069 · 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. In
Mitigations
- Limit Public Release of Information
- Control Access to AI Models and Data at Rest
- Control Access to AI Models and Data in Production
- Generative AI Guardrails
Detections 1
Related techniques
- LLM07 System Prompt Leakage OWASP LLM
In the news
No stories mapped to this technique yet.
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.