MITRE ATLASsub-technique
AML.T0069.001 System Instruction Keywords
- Tactics
- Discovery
- Created
- 2025-03-12
Description
Adversaries may discover keywords that have special meaning to the large language model (LLM), such as function names or object names. These can later be exploited to confuse or manipulate the LLM into misbehaving and to make calls to plugins the LLM has access to.
Related
Subtechnique of · MITRE ATLAS (1)
- AML.T0069 Discover LLM System Information technique
Tactic · MITRE ATLAS (1)
- AML.TA0008 Discovery tactic