llm-prompt-injection

LLM prompt injection playbook. Use when testing AI/LLM applications for direct injection, indirect injection via RAG/browsing, tool abuse, data exfiltration, MCP security risks, and defense bypass techniques.

Try your first task

A source-grounded starter task has not been verified for this skill yet.

Inside SKILL.md

357 lines

Section content has not been verified for this skill yet.

Full source remains withheld under the current source-display policy. Read the author’s source ↗