Individual skill

prompt-injection-defense

Defend LLM systems against prompt injection — attack taxonomy, input handling, output validation, and layered mitigations. Use when building LLM features that process untrusted input. Defensive only.

skills/prompt-injection-defense/SKILL.md

Read pinned source

Source commit faf37c0859ebf627bfcb5225e8057d088691e0ae

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: Yes
Observed behavior: Not checked yet
Last checked: Nov 8, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 54
Repository last updated: Oct 10, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent-skills Repository topic
ai-agents Repository topic
ai-agents-automation Repository topic
ai-skills Repository topic
awesome Repository topic
awesome-list Repository topic
chatgpt Repository topic
claude-skills Repository topic
meta-ai Repository topic
muse-ai Repository topic
operations Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 4,401 bytes

Read excerpt


# Prompt Injection Defense

Prompt injection: malicious instructions hidden in data the model processes — webpages, 
documents, tool outputs, user messages — that hijack the model's behavior. This skill is 
defensive: understand the attack shapes so you can build systems that resist them.

## Overview

The core vulnerability: models can't reliably distinguish instructions from data — everything is 
text. Attacks exploit this: direct injection (malicious user input), indirect injection (poisoned 
webpages, documents, or tool outputs the model reads), and multi-step variants (instructions split 
across turns or sources). Defense is layered because no single layer is reliable: structure inputs, 
validate outputs, limit authority, and monitor.