AgentShield: Security Auditor for Claude Code and MCP Configurations

Repositoryaffaan-m/agentshieldTool

AgentShield is an open-source TypeScript security scanner designed for AI agent setups. It inspects `.claude/` directories to detect hardcoded secrets, unverified MCP servers, hook injection vulnerabilities, and tool permission misconfigurations.

Key points

  1. Scans `~/.claude/` configuration files automatically via CLI, GitHub Action, or GitHub App integration.
  2. Detects hardcoded API credentials, hook injection flaws, permissive tool configs, and agent prompt injection vectors.
  3. Audits Model Context Protocol (MCP) servers and automatically ignores generated directories like `node_modules`.
  4. Includes an optional deep analysis pipeline powered by Opus.
  5. Created during the Claude Code Hackathon in February 2026 as part of the 'Everything Claude Code' ecosystem.

Why it matters

The rapid growth of AI developer agents and community-contributed MCP tools has created new attack vectors. Unchecked setups expose local developer environments to remote code execution and credential leakage via malicious extensions and misconfigured agent hooks.

Analysis

AgentShield brings standard DevSecOps practices to the emerging space of AI agent tooling. By offering zero-install scanning via npx alongside GitHub Actions, it simplifies security hygiene for developers using Claude Code. With more than 1,100 stars and an active tie-in with the 'Everything Claude Code' suite, it represents a promising, practical utility that meets an immediate need created by rapid agent adoption in 2026.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:NVIDIA/SkillSpector

    SkillSpector: Security Scanner for AI Agent Skills by NVIDIA

    SkillSpector is an open-source security scanner from NVIDIA designed to inspect extensions and skills for AI agents (such as Claude Code, Codex CLI, and MCP) for vulnerabilities and malicious patterns before installation.

    15.9kstarsPython

    AI & LLMs· Tool

  • Link:ecc.tools

    ECC Tools: Open Harness System and GitHub App for Coding Agents

    ECC Tools provides a cross-platform harness system for coding assistants such as Claude Code, Codex, Cursor, and OpenCode. It combines an open-source toolkit, an Opus 4.6-powered security auditor called AgentShield, and a GitHub App that transforms repository history into reusable skills.

    AI & LLMs· Tool

  • Repository:bex-co/bex-security

    Bex Security: Agent-Agnostic AI Security Scanner

    Bex Security is an open-source, upstream-first fork of OpenAI Codex Security that brings vulnerability detection, validation, and remediation to multiple coding agents via the Agent Client Protocol (ACP).

    51starsTypeScript

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.