Repository Security Gate

    1

    Review repositories, agent skills, plugins, MCP servers and dependencies before installing or running them. Identify credential leaks, suspicious behavior and supply-chain risks, with scoped findings and safer fixes.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    About this skill

    Repository Security Gate is an MIT-licensed agent workflow for reviewing repositories, skills, plugins, MCP servers and dependencies before installation or execution.

    It guides inspection of installer hooks, scripts, dependencies, credential exposure, sensitive-file access, network destinations and prompt-injection risks. It reports confirmed findings, proposed reversible fixes and coverage gaps using BLOCKED, PENDING or CLEARED FOR REVIEWED INSTALL outcomes.

    This is an agent workflow, not a standalone scanner or continuous monitoring tool. It cannot guarantee safety. Dynamic checks require verified isolation and synthetic data.

    MIT License, copyright (c) 2026 animesh8555; LICENSE is included. Source: https://github.com/animesh8555/repo-security-gate

    Requires local source access. Cannot intercept commands outside the agent workflow. Coverage gaps exist for unreviewed Git history or obfuscated binaries.

    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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed today

    • Free with an Agensi account

    Requires

    SKILL.md-compatible coding agent with local file and terminal tools. No bundled runtime or mandatory external subscription.
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Browser
    Network Access

    Access is limited to the user-authorized review scope. Do not collect real credentials or scan the whole drive. No specific account connection is mandatory. Network checks and file modifications depend on the requested audit and repair scope.

    Listedtoday

    What's inside

    Frequently Asked Questions

    An agent workflow for reviewing source and installation behavior before execution. It cannot block commands outside the workflow or guarantee safety.

    Coverage depends on the agent, tools, accessible source and available scanners. No language-specific scanner is bundled.

    Material inaccessible dependencies, unknown binaries or unresolved obfuscation prevent clearance. Report the gaps and use BLOCKED or PENDING as appropriate.

    A reusable review checklist with rules for untrusted source, reversible fixes and scoped outcomes. The agent must follow it; it does not independently enforce commands.

    No external subscription is declared. Use trusted local tools and official advisory sources where available; report missing tools and advisory coverage.

    New in Security

    Free