mole

Detects and tags planted instructions in untrusted text to prevent AI hijacking.

6|1|Updated Jun 23, 2026

Search Tags:#AI security #text analysis #prompt injection #security detection #untrusted text

Ready to run

npx skills add https://github.com/JGalego/Bag-of-Tricks --skill mole-jgalego

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: mole
Source: https://github.com/JGalego/Bag-of-Tricks/tree/main/mole
Command: npx skills add https://github.com/JGalego/Bag-of-Tricks --skill mole-jgalego

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill identifies and tags potential harmful instructions hidden in untrusted text, preventing them from influencing the AI's processing.

Core Features & Use Cases

Detects Planted Instructions: Identifies instruction overrides, role spoofing, persona jailbreaks, and prompt-leak attempts.
Input-side Protection: Monitors incoming text for planted commands that could hijack AI behavior.
Use Case: If you receive a document with untrusted text, you can use the mole skill to scan for hidden instructions before processing the content.

Quick Start

Run the 'mole' skill on a text snippet to detect planted instructions.

Frequently Asked Questions about mole

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

FAQPage Schema

How do I detect prompt injection attacks in untrusted text before processing?▼

Identify prompt injection by scanning untrusted text for planted instructions such as role spoofing, persona jailbreaks, and instruction overrides to prevent AI hijacking at the input stage.

What exactly is a persona jailbreak in AI security and how does it hijack behavior?▼

A persona jailbreak is a planted instruction within untrusted text that attempts to override the AI's assigned role, hijacking behavior by forcing it to adopt an unauthorized persona.

How do I scan a document for hidden instructions and role spoofing before feeding it to an AI?▼

To scan a document for hidden instructions and role spoofing, run an input-side security detection process that tags instruction overrides and prompt-leak attempts before AI processing.

Does input-side security detection work for preventing instruction overrides in untrusted text?▼

Input-side security detection works for preventing instruction overrides by operating at the text input stage to identify and tag harmful commands before they influence AI processing.

What is the best way to prevent AI hijacking from prompt-leak attempts in external documents?▼

The best way to prevent AI hijacking from prompt-leak attempts is to scan untrusted text inputs to identify and tag planted instructions before the AI processes the content.

What are the limitations of detecting planted instructions using text analysis?▼

Detecting planted instructions via text analysis is limited to identifying known patterns like role spoofing and instruction overrides at the input stage, and may miss novel or obfuscated prompt injection techniques.