skills.rest
thejefflarson
thejefflarsonCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

prompt-injection

Detect and fix prompt construction patterns that allow user input to influence system prompts.

20|Updated Feb 27, 2026
Search Tags:#rag#input-validation#system-prompt#security-review#prompt-injection#llm-security
One-click install
npx skills add https://github.com/thejefflarson/soundcheck --skill prompt-injection
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: prompt-injection
Source: https://github.com/thejefflarson/soundcheck/tree/main/.claude/skills/prompt-injection
Command: npx skills add https://github.com/thejefflarson/soundcheck --skill prompt-injection

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Protects against attacker-controlled text that hijacks LLM instructions. Direct injection arrives through user input; indirect injection arrives through retrieved documents, emails, or tool outputs. Both can cause the model to exfiltrate data, bypass guardrails, or execute unintended actions.

Core Features & Use Cases

  • Detect vulnerable patterns where user data bleeds into system prompts
  • Enforce boundaries by placing user data and retrieved documents in explicit segments
  • Support RAG pipelines and external document processing with safe prompts

Quick Start

Identify and fix prompt construction patterns that allow user input to influence the system prompt, then reorganize prompts to separate developer instructions from data and wrap retrieved content with explicit delimiters.

Frequently Asked Questions about prompt-injection

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
What is prompt injection and how does it affect LLM security?▼

Prompt injection is an attack where attacker-controlled text hijacks LLM instructions, causing data exfiltration or guardrail bypasses via direct user input or indirect retrieved documents.

How do I prevent user input from hijacking system prompts in my application?▼

Prevent hijacking by enforcing boundaries that separate developer instructions from untrusted data, and wrap retrieved content in explicit delimiters before processing downstream.

How do I secure RAG pipelines against indirect prompt injection?▼

Secure RAG pipelines by wrapping retrieved documents in explicit delimiters and validating inputs and outputs before any downstream use to isolate untrusted content.

Does this approach work for processing external documents fed to a model?▼

Yes, this approach applies to code that processes external documents fed to a model, enforcing separation of developer instructions from untrusted data to prevent leakage.

Why do I need input validation for prompt construction patterns?▼

Input validation is needed to detect vulnerable patterns where user data bleeds into system prompts, ensuring retrieved content and user inputs are validated before downstream use.

What is the best way to structure prompts to avoid data leakage?▼

The best way to avoid data leakage is to reorganize prompts by separating developer instructions from data and wrapping retrieved content with explicit delimiters.

Related Skills

Explore More Software Engineering Skills→
ShankulkarniShankulkarni
1

audit-llm-prompt-injection

Audit LLM applications for prompt injection and secret exposure.

Community
Advanced
MuvonMuvon
3

ai-prompt-injection-defense

Audit LLM injection surfaces and produce OWASP-aligned defense recommendations.

Official
Advanced
Sir-chawakornSir-chawakorn
9

defend-llm-prompt-injection

Enforce trust boundaries with input/output guardrails and delimiter-based data isolation.

Community
Advanced
ricardorochericardoroche
2

ai-security

Detect prompt injection attempts in AI and LLM applications.

Community
Intermediate