More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    secret sentinel

    1

    Prevent and remediate credential leaks in code, logs, and agent prompts using local MCP scanning and redaction.

    Free

    1 useSecurity scanned
    secret sentinel

    secret sentinel

    Example session with this skill installed

    I'm about to commit these changes to my billing module. Can you check them for secrets first?

    • Read your context and instructions
    • Compiled the secret sentinel

    I have scanned your staged changes using scan_git_staged. I found one high-severity finding in your configuration file that needs to be addressed before you commit.

    Security Scan Results

    FileLineDetectorSeverityRedacted Finding
    config/billing.py12stripe-api-keyhighsk_live_... (32 chars)
    config/billing.py15generic-api-keymediumAIzaSy... (20 chars)

    The scan identified a live Stripe API key hardcoded in your billing configuration. Even if you delete this in a later commit, the secret will remain in your git history.

    Recommended Fix:

    1. Move the Stripe key to a .env file (ensure .env is in your .gitignore).
    2. Update config/billing.py to use os.environ["STRIPE_API_KEY"].
    3. Since this key was visible to the agent, you should rotate it in your Stripe dashboard immediately.

    Next steps

    • Replace the literal strings in config/billing.py with environment variable lookups.
    • Run mcp-secret-sentinel scan --staged again to verify the fix.
    • Install the pre-commit hook with mcp-secret-sentinel install-hook to prevent this in the future.

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

    About this skill

    Credentials pushed to a repository or pasted into a prompt are compromised instantly, even if you delete them in the next commit. Secret Sentinel prevents these leaks before they happen and provides a systematic remediation path when exposures occur. It integrates directly into your agentic workflow to ensure API keys, tokens, and private keys never leave your local environment or enter your logs.

    What it does

    • Proactive scanning checks staged git changes, full directories, or specific files for over 64 types of credentials.
    • Automated redaction cleans logs, stack traces, and command outputs by replacing secrets with redacted placeholders before you share them.
    • Configuration auditing scans MCP client configs, .mcp.json, and agent instructions to ensure no credentials are hardcoded in repo-tracked files.
    • Remediation playbooks provide step-by-step guidance for rotating compromised keys and cleaning git history.
    • Pre-commit enforcement installs local hooks to block any commit that contains a detected secret.

    How it works

    1. Use scan_git_staged or scan_git_range before every commit or push to verify your changes are clean.
    2. Run redact_text on any terminal output or log file before quoting it in a prompt or sharing it with the agent.
    3. Replace hardcoded literals with environment variable lookups like os.getenv or process.env based on the detected finding.
    4. Apply the install-hook command to automate local guardrails for the entire project.

    Frameworks & tools

    Built for Python 3.10+ and available as both an MCP server and a CLI. It supports major agent environments including Claude Code and Cursor, with a dedicated GitHub Action for CI/CD integration.

    Why this beats prompting it yourself

    Generic prompts often miss base64-encoded secrets or high-entropy strings that don't look like standard keys. This skill uses a specialized engine with 64 specific detectors and base64-aware scanning, ensuring that "security through obscurity" doesn't lead to a breach.

    Use cases

    • Pre-flight checks to scan all staged files before running git commit.
    • Log sanitization to strip sensitive tokens from a crash report before sending it to an AI for debugging.
    • Agent config hardening to ensure your MCP server settings aren't leaking keys into your repository.
    • Incident response to walk through a structured rotation and history cleanup after an accidental push.

    Known limitations

    Scanning requires the secret-sentinel MCP server or CLI to be installed locally. The scanner may truncate output in extremely large repositories, showing only the most severe findings.

    Requires Python 3.10+ for the scanner. Scans may be truncated in large repos to show only high-severity findings. Manual setup is needed for git hooks.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 28 days ago

    • Free with an Agensi account

    Requires

    Python
    uv (Python tool runner)
    Git

    Permissions

    Read Files
    Write Files
    Network Access
    Environment Variables
    Listed28 days ago

    What's inside

    Frequently Asked Questions

    Secret Sentinel acts as a local security layer that scans code and logs for over 64 types of credentials, automatically redacting them before they reach your AI agent or are committed to a repository. It solves the critical problem of 'instant compromise' by blocking leaks before data leaves your local machine.

    The skill is designed for any environment supporting Model Context Protocol (MCP), including Claude Code and Cursor. It also includes a CLI and a GitHub Action, making it compatible with most modern development workflows and CI/CD pipelines.

    No, scanning and redaction are performed locally using the Secret Sentinel MCP server or CLI. Your sensitive data is processed on your machine, ensuring that unredacted secrets are never sent to external servers or AI models for analysis.

    Your purchase includes the full Secret Sentinel MCP server, a standalone CLI tool, a dedicated GitHub Action for repository protection, and a library of remediation playbooks for incident response.

    Yes, the 'install-hook' command sets up local git hooks that automatically trigger a scan during the pre-commit phase. This ensures that any commit containing a detected secret is blocked until the security risk is addressed.

    While the scanner is highly efficient, it may truncate output in extremely large repositories to prioritize the most severe findings. It requires Python 3.10+ and a local installation of the Secret Sentinel server to function within your agentic workflow.

    New in LLM Ops