Prompt Injection (Direct)
Direct prompt injections are adversarial attacks that attempts to alter or control the output of an LLM by providing instructions via prompt that override existing instructions. These outputs can include harmful content, misinformation, or extracted sensitive information such as PII or model instructions.
Input / output filtering
MITRE ATLAS
AML.T0051.000 - LLM Prompt Injection: Direct
OWASP TOP 10 for LLM Applications
LLM01 - Prompt Injection