system-prompt-leakage-reviewer

Community

Stop prompt leaks from becoming security gaps.

Authornguyenpv1980-wq
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill reviews an LLM system or developer prompt for leaked secrets and for dangerous reliance on prompt secrecy as a security control, so hidden instructions do not become a security weakness.

Core Features & Use Cases

  • Secret Detection in Prompts: Identifies API keys, credentials, connection strings, internal endpoints, and other sensitive details embedded in the prompt.
  • Prompt-as-Control Review: Finds security rules like admin-only access, pricing limits, or refusal policies that must be enforced by real code instead of the model.
  • Security Routing Guidance: Directs leaked secrets to rotation and prompt-based controls to deterministic enforcement outside the model.
  • Use Case: A team asks whether their system prompt is safe because it contains an internal API key and an admin-only rule; this Skill flags both issues and points to the correct owning controls.

Quick Start

Ask the system-prompt-leakage-reviewer to assess this prompt for leaked secrets and any security rules that depend on the prompt staying secret.

Dependency Matrix

Required Modules

None required

Components

references

💻 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: system-prompt-leakage-reviewer
Download link: https://github.com/nguyenpv1980-wq/Project-Aegis/archive/main.zip#system-prompt-leakage-reviewer

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 545,000+ vetted skills library on demand.