LLM Direct Prompt Injection

Test Large Language Models for direct prompt injection vulnerabilities where user input overrides system instructions, extracts system prompts, bypasses safety filters, or causes unauthorized actions. Use this skill when assessing chatbots, AI assistants, LLM-powered tools, or any application that processes natural language input through an LLM. Covers role-playing attacks, instruction hierarchy exploitation, multi-turn manipulation, and context window abuse for comprehensive AI security testing.

ShulkwiSEC Updated 27 repo stars
Demo

File contents

ShulkwiSEC/bb-huge commit 6a17e72578 Runs: shulkwisec/llm-training-data-extractionshulkwisec/llm-indirect-prompt-injection

Frequently asked questions

npx get-skill add shulkwisec/llm-direct-prompt-injection