Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    AgentShield — AI Skill & MCP Security Scanner

    3

    Static security scanner for MCP servers and AI skills to detect over-privileged permissions, secrets, and code risks.

    $9.99

    /mo

    Subscription · cancel anytime

    Secure checkout via Stripe

    • Always the latest version
    • Delivered live to your agent via MCP
    • Cancel anytime, access ends at period end
    Security scanned
    AgentShield — AI Skill & MCP Security Scanner

    AgentShield — AI Skill & MCP Security Scanner

    Example session with this skill installed

    Scan the new mcp-server-sqlite directory I just downloaded for security risks before I add it to my Claude config.

    • Read your context and instructions
    • Compiled the agentshield

    I have completed the static security analysis of the mcp-server-sqlite directory. The scan identified 4 findings across tool schemas and configuration files.

    Security Analysis Report: mcp-server-sqlite

    SeverityRule IDFileEvidenceRecommendation
    HIGHEXEC-01server.py:42subprocess.run(user_input, shell=True)Remove shell execution; use parameterized queries for DB operations.
    MEDIUMNET-02mcp-config.jsonallowed_hosts: ["*"]Restrict network access to specific local or trusted DB endpoints.
    LOWFS-01schema.jsonwrite_access: trueVerify if the skill requires write permissions for your specific use case.
    INFOSEC-05.env.exampleDB_PASSWORD=...Ensure actual credentials are not committed to version control.

    Permissions & Capabilities Summary

    • Filesystem: Read/Write access detected in specific working directory.
    • Network: Unrestricted host access configured in JSON manifest.
    • System: Ability to spawn shell processes (High Risk).
    • Secrets: No active secrets leaked; template keys found.

    Risk Assessment

    • Overall Risk: HIGH
    • Findings: 1 High, 1 Medium, 1 Low, 1 Info.
    • Status: Baseline match failed (New Installation).

    Next steps

    1. Refactor server.py to remove shell=True before running the server.
    2. Update the mcp-config.json to whitelist only localhost or specific database IPs.
    3. Run the scan again after applying fixes to verify the risk reduction.
    $9.99/mo

    Subscription · always the latest version

    • Secure checkout via Stripe
    • Cancel anytime
    • Delivered live via MCP

    About this skill

    Running untrusted AI skills or MCP servers on your local machine is a significant security risk. This skill performs defensive static analysis to identify vulnerabilities, over-privileged permissions, and malicious patterns before you install new agent capabilities.

    What it does

    • Permission Auditing identifies excessive filesystem, network, and environment variable access.
    • Secret Detection flags hardcoded credentials or dangerous secret-handling patterns without exposing the values.
    • Injection Analysis scans for prompt injection indicators and suspicious instructions inside agent assets.
    • Execution Risk detects shell command execution, hidden scripts, and arbitrary code patterns.
    • Supply Chain Review evaluates tool schemas and MCP configurations for external dependencies and risks.

    How it works

    1. Point the agent to an AI skill directory, MCP config file, or tool schema.
    2. The skill performs a static scan of the assets, scripts, and configuration files.
    3. It categorizes findings by severity from Low to Critical with specific evidence.
    4. You receive a structured security report including a permissions summary and remediation steps.

    Frameworks & tools

    This skill works with MCP (Model Context Protocol) servers, JSON tool schemas, Python/Node.js agent scripts, and standard configuration files like mcp-config.json.

    Why this beats prompting it yourself

    Manual inspection often misses subtle permission overlaps or obfuscated shell commands. This skill uses a structured risk model and mandatory reporting format to ensure every capability is explicitly accounted for and categorized by threat level.

    Use cases

    • Auditing a third-party MCP server before adding it to your Claude Desktop config.
    • Reviewing a downloaded AI skill from a marketplace for hidden network calls.
    • Checking local agent scripts for hardcoded API keys or wide file-system write access.
    • Benchmarking a new version of a tool against a known secure baseline.

    Known limitations

    Static analysis cannot guarantee the detection of all runtime malware or dynamic execution paths. It does not execute code or connect to endpoints to verify behavior.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.

    Does not perform dynamic analysis or runtime sandboxing. Cannot identify malware hidden in compiled binaries or encrypted payloads. Requires local access to source files or configs.

    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 buying a skill.

    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 to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Software
    Python

    Permissions

    Terminal / Shell
    Network Access
    Environment Variables
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    The scanner supports MCP (Model Context Protocol) servers, JSON tool schemas, and agent scripts written in Python or Node.js, making it compatible with environments like Claude Desktop and custom LLM frameworks.

    No, the skill performs defensive static analysis, meaning it reviews code and configuration files without executing them, ensuring your system remains safe during the audit process.

    The scanner identifies over-privileged filesystem and network permissions, hardcoded credentials, potential prompt injection vectors, and suspicious shell command execution patterns.

    While basic prompts may miss obfuscated commands or complex permission overlaps, this skill uses a structured risk model and mandatory reporting format to ensure no threat category is overlooked.

    Each scan generates a structured security report that categorizes findings by severity (Low to Critical), provides a summary of requested permissions, and suggests specific remediation steps.

    This skill is designed to audit local files and configurations; it does not connect to external endpoints or verify runtime behavior of live APIs.

    New in Security