Glossary: AI Security and Guardrails
Hidden Context Exposure
Also written: LLM08, System Prompt Leakage
Revealing context the user isn't meant to see, starting with the system prompt. Design as if every word of the prompt is public.
Glossary: AI Security and Guardrails
Also written: LLM08, System Prompt Leakage
Revealing context the user isn't meant to see, starting with the system prompt. Design as if every word of the prompt is public.