sensitive-disclosure

Community

Guard confidential data in LLM interactions.

Authorthejefflarson
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Prevents leakage of sensitive data (PII, credentials, health information) when prompts are passed to LLMs or model outputs may expose secrets. It provides redaction, secrets management, and memory isolation to safeguard data.

Core Features & Use Cases

  • Redaction and pseudonymization of inputs before prompts reach the model.
  • Secrets management to keep credentials off prompts and prompts only reference safe tokens.
  • Output redaction and memory isolation to avoid leaking data in responses or stored session state.
  • Use Case: When building AI-assisted tools that handle user data in customer support, analytics, or automation workflows.

Quick Start

Redact sensitive input data and ensure secrets never reach the model.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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: sensitive-disclosure
Download link: https://github.com/thejefflarson/soundcheck/archive/main.zip#sensitive-disclosure

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 471,000+ vetted skills library on demand.