data-leakage-detection

Official

Guard against sensitive data leaks.

AuthorTencent
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill proactively identifies and prevents the accidental or malicious disclosure of sensitive information by AI models, safeguarding confidential data.

Core Features & Use Cases

  • System Prompt Extraction Detection: Checks if the AI's core instructions are being revealed.
  • Credential & PII Leakage Detection: Probes for exposed API keys, passwords, personal identifiable information, and internal configurations.
  • Escalating Probes: Employs a multi-phase approach, starting with direct questions and progressing to more sophisticated evasion techniques if necessary.
  • Use Case: Ensure your AI chatbot does not inadvertently reveal internal API endpoints or customer PII during conversations.

Quick Start

Use the data-leakage-detection skill to check for any system prompt disclosure.

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: data-leakage-detection
Download link: https://github.com/Tencent/AI-Infra-Guard/archive/main.zip#data-leakage-detection

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 223,000+ vetted skills library on demand.