skills.rest
nguyenpv1980-wq
nguyenpv1980-wqCOMMUNITY
Explore all skills by this author →
GitHub

sensitive-disclosure-guard

Redact sensitive data before AI model processing and audit leak paths.

2|Updated Jul 6, 2026
Search Tags:#redaction#pii#leak detection#llm security#data minimization#sensitive data
One-click install
npx skills add https://github.com/nguyenpv1980-wq/Project-Aegis --skill sensitive-disclosure-guard
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sensitive-disclosure-guard
Source: https://github.com/nguyenpv1980-wq/Project-Aegis/tree/main/.claude/skills/sensitive-disclosure-guard
Command: npx skills add https://github.com/nguyenpv1980-wq/Project-Aegis --skill sensitive-disclosure-guard

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps prevent an AI feature from disclosing sensitive information such as PII, secrets, credentials, regulated data, or other-tenant data through model context, outputs, logs, or provider handling.

Core Features & Use Cases

  • Data Minimization: Replaces whole-record context dumps with only the fields the task actually needs.
  • Pre-Model Redaction: Designs stripping and masking pipelines for user input, retrieved content, and tool outputs before they reach the model.
  • Leak Path Review: Checks for output echo, inference leaks, cross-user or cross-conversation bleed, and unsafe prompt logging.
  • Provider Posture Review: Confirms retention, training-on-inputs, and residency constraints are acceptable for the data being used.
  • Use Case: A support assistant that currently sends full customer records to an LLM can be redesigned to send only necessary fields, redact sensitive values, and verify that logs and responses do not expose private data.

Quick Start

Ask the skill to review your AI feature for sensitive-data exposure and propose a least-data, pre-model redaction design with leak checks for output, logs, and provider posture.

Frequently Asked Questions about sensitive-disclosure-guard

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

FAQPage Schema
How do I prevent PII and sensitive data from leaking into LLM context and outputs?▼

Data minimization replaces whole-record context dumps with only the fields the task actually needs, reducing the exposed surface area before any redaction is applied. This Skill implements least-data assembly to ensure only necessary fields are sent to the model.

What is data minimization for AI features and how does it reduce sensitive data exposure?▼

Data minimization replaces whole-record context dumps with only the fields the task actually needs, reducing the exposed surface area before any redaction is applied. This Skill implements least-data assembly to ensure only necessary fields are sent to the model.

How do I audit leak paths for cross-user bleed and unsafe prompt logging in AI assistants?▼

Provider posture review confirms retention, training-on-inputs, and residency constraints are acceptable for the data being used. This Skill evaluates your provider's handling policies to ensure sensitive data is not retained or used for training.

How do I verify LLM provider retention and training-on-inputs posture for regulated data?▼

Provider posture review confirms retention, training-on-inputs, and residency constraints are acceptable for the data being used. This Skill evaluates your provider's handling policies to ensure sensitive data is not retained or used for training.

What's the best way to redact sensitive values in tool outputs before they reach the model?▼

Pre-model redaction designs stripping and masking pipelines for user input, retrieved content, and tool outputs before they reach the model. This Skill builds those pipelines to intercept and redact sensitive values prior to LLM processing.

Does this approach work for support assistants processing full customer records with PII?▼

A support assistant that sends full customer records to an LLM can be redesigned to send only necessary fields, redact sensitive values, and verify logs and responses do not expose private data. This Skill applies to features processing PII, secrets, credentials, and other-tenant information.

Related Skills

Explore More Software Engineering Skills→
0x1337c0d30x1337c0d3
3

attack-surface

Identifies and inventories external data entry points, classifying them by authentication, input types, validation, risk factors, and exposure for integration with Sentinel's scanning pipeline and risk scoring system.

Community
Advanced
thejefflarsonthejefflarson
20

sensitive-disclosure

Redact PII and credentials from inputs before LLM usage.

Community
Intermediate
jota-batutajota-batuta

llm-pipeline-design

Design end-to-end LLM pipelines with Langfuse tracing and auto-supervision.

Community
Advanced
truefoundrytruefoundry
13

guardrails

Configure content safety guardrails for AI Gateway endpoints.

Official
Advanced