credential-leak-detector

Community

Stop secret leaks before they hit chat

AuthorJKHeadley
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Bash output can expose API keys, private keys, tokens, and passwords to the conversation, logs, and context windows before anyone notices. This Skill catches those leaks immediately so sensitive values do not spread further.

Core Features & Use Cases

  • Critical blocking: Stops outputs containing live credentials like OpenAI keys, AWS keys, GitHub tokens, Stripe secrets, and PEM private keys.
  • Redaction and warnings: Masks high-severity matches and flags suspicious patterns such as bearer tokens, auth strings, and high-entropy secrets.
  • Post-tool-use protection: Works after a Bash command runs, which makes it ideal for diagnostics, container inspection, Kubernetes output, and any command that may print hidden secrets.

Quick Start

Ask the assistant to install this hook so every Bash command output is scanned for secrets, critical leaks are blocked, and suspicious values are redacted or flagged before they appear in chat.

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: credential-leak-detector
Download link: https://github.com/JKHeadley/instar/archive/main.zip#credential-leak-detector

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 536,000+ vetted skills library on demand.