Types of LLM vulnerabilities | Promptfoo
This page documents categories of potential LLM vulnerabilities and failure modes.| www.promptfoo.dev
This page documents categories of potential LLM vulnerabilities and failure modes.| www.promptfoo.dev
The Harmful Content plugin is designed to test an AI system's ability to handle and respond appropriately to various types of harmful or sensitive content. This plugin covers a wide range of potentially problematic areas, from violent crimes to misinformation.| www.promptfoo.dev
