Secret Leak Guard

    2

    Locally scan your repository for leaked API keys, tokens, and secrets before committing or publishing code.

    $15

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Secret Leak Guard

    Example session with this skill installed

    Check my current directory for any leaked API keys or secrets before I commit these changes.

    • Read your context and instructions
    • Compiled the secret leak guard

    Found 2 potential secrets:

    • .env:7 | AWS_SECRET_KEY | [REDACTED_AKIA...]
    • src/config.js:12 | Stripe API Key | [REDACTED_sk_test...]
      Total findings: 2. Please rotate these credentials before pushing.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    What it does

    Secret Leak Guard provides a high-performance, local-first scanning layer to prevent credentials, API keys, and sensitive tokens from ever leaving your machine. It identifies high-entropy strings and known secret patterns within your codebase before they are pushed to remote repositories.

    Why use this skill

    Relying on generic LLM prompts for security is risky; they can miss subtle patterns or fail to prioritize leaked data correctly. This skill automates the detection process with precision, providing masked findings to ensure the AI agent itself doesn't inadvertently log the full secret. It is essential for maintaining compliance and preventing 0-day credential leaks.

    Supported Environment

    • Works across any local directory or Git repository
    • Supports modern development environments like Cursor, Claude Code, and VS Code
    • Optional JSON output for integration into CI/CD pipelines or custom developer workflows
    • Zero network calls for scanning, ensuring complete data privacy

    The Output

    You receive a clean, actionable report of potential leaks, categorized by file and line number, with sensitive values safely masked for review.

    • May produce false positives on high-entropy non-secret strings.
    • Local scan only; does not verify if secrets are active.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 6 months ago

    Software
    Python

    Permissions

    Terminal / Shell
    Listed6 months ago

    What's inside

    Frequently Asked Questions

    Secret Leak Guard performs high-entropy scanning and pattern matching locally on your machine, preventing sensitive credentials from being sent to the LLM or pushed to remote repositories.

    The skill is designed for local directories and Git repositories, making it compatible with AI coding environments like Cursor, Claude Code, and VS Code.

    No, all scanning is performed offline and locally on your hardware; the skill never transmits your raw codebase or your secrets over the network.

    The output provides a categorized report by file and line number, with the actual secret masked (e.g., 'sk-live-****') to protect the value while allowing you to identify it.

    Setup is streamlined for immediate use in local workflows; you simply grant the agent access to the target directory and trigger the scan via a natural language command.

    Your purchase includes the full skill set for secret detection, detailed integration instructions, and access to any future pattern updates to catch newly released API formats.

    New in Security