prism-sanitize

Community

Enhance prompt security and compliance with advanced sanitization analysis.

AuthorCraigHutchinson
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides internal sanitization analysis to enhance prompt security and compliance, preventing data leaks and improving prompt quality.

Core Features & Use Cases

  • PII Scan: Detects Personally Identifiable Information (PII) in prompts.
  • Semantic Analysis: Checks for semantic issues like ambiguous authority statements and indirect injections.
  • Output Formatting: Returns findings in structured JSON format for further processing.

Quick Start

To begin sanitization analysis, execute the following commands: python scripts/pii_scan.py --json "<prompt>" and reference sanitization rules with cat .cursor/skills/prism/sanitization-rules.md.

Dependency Matrix

Required Modules

python

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: prism-sanitize
Download link: https://github.com/CraigHutchinson/Prism/archive/main.zip#prism-sanitize

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.