skills.rest
maruakshay
maruakshayCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

core-llm-prompt-security

Identify and mitigate prompt injection and jailbreak risks in LLM prompts.

4|Updated Apr 27, 2026
Search Tags:#validation#injection#jailbreak#guardrails#security-review#prompt-security#trust-boundary
One-click install
npx skills add https://github.com/maruakshay/mii-ai-security --skill core-llm-prompt-security
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: core-llm-prompt-security
Source: https://github.com/maruakshay/mii-ai-security/tree/main/skills/core-llm-prompt-security
Command: npx skills add https://github.com/maruakshay/mii-ai-security --skill core-llm-prompt-security

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Review the core prompt layer of an LLM application for prompt injection, jailbreaks, system prompt exposure, weak guardrails, unsafe output handling, and trust-boundary failures across any language or framework.

Core Features & Use Cases

  • Identify and label input boundaries between trusted instructions and untrusted content.
  • Validate and isolate system prompts from user content to prevent leakage and manipulation.
  • Provide guardrails and failure-mode coverage across prompt processing, input handling, and output parsing.

Quick Start

Run a security review by loading the SKILL.md into your security review workbook and applying boundary and validation checks.

Frequently Asked Questions about core-llm-prompt-security

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

FAQPage Schema
How do I prevent prompt injection and jailbreaks in my LLM application?▼

To prevent prompt injection, you must enforce a structured separation between trusted system instructions and untrusted user content using boundary labeling, input validation, and guarded output handling.

What is a prompt trust boundary and how does it secure LLM prompts?▼

A prompt trust boundary labels and isolates trusted system prompts from untrusted user content, preventing manipulation and system prompt exposure across your LLM application deployments.

How do I perform a security review of my LLM system prompts?▼

Perform a security review by applying boundary and validation checks across your codebase to surface prompt-injection, weak guardrails, and unsafe output handling failures.

Does this prompt security review work across any language and framework?▼

Yes, the prompt security review can be applied across any language or framework to identify jailbreak risks, system prompt exposure, and trust-boundary weaknesses.

How do I validate and isolate system prompts from user content?▼

Validate and isolate system prompts by enforcing input boundaries that separate trusted instructions from untrusted content, preventing leakage and manipulation during prompt processing.

What are the limitations of using guardrails for prompt security?▼

Guardrails for prompt security focus on boundary labeling and validation but require consistent application across input handling and output parsing to prevent trust-boundary failures.

Related Skills

Explore More Software Engineering Skills→
thejefflarsonthejefflarson
20

prompt-injection

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

Community
Intermediate
jonnabiojonnabio
6

prompt-guard

Detect prompt injection and jailbreak attempts in LLM applications.

Community
Advanced
uphiagouphiago
1.1k

hunt-llm-ai

Identify exploitable LLM/AI vulnerabilities crossing trust boundaries with validation gates.

Community
Advanced
tianhao909tianhao909
1

prompt-guard

Detect prompt injections and jailbreak attempts in user inputs.

Community
Advanced