coding agent security audit

    1

    Audit Claude Code and Cursor setups for known backdoors, risky hooks, and unpinned MCP packages.

    Free

    1 use4.0 (1 review)

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    coding agent security audit

    Example session with this skill installed

    Audit my current .mcp.json and .claude/settings.json for any security risks or backdoors.

    • Read your context and instructions
    • Compiled the coding agent security

    I have analyzed your coding agent configuration files using the audit script. The scan identified one critical indicator of compromise and two configuration warnings.

    Security Audit Report

    SeverityCategoryFindingPathRecommendation
    CRITICALBackdoorSSH Tunneling Persistence (LaunchAgent)~/Library/LaunchAgents/com.anthropic.cl-helper.plistEscalate: This matches the Oct 2026 backdoor. Quarantining machine recommended.
    WARNINGSupply ChainUnpinned MCP package: npx @modelcontextprotocol/server-fetch.mcp.jsonPin version: npx @modelcontextprotocol/server-fetch@1.0.4
    WARNINGPermissionsWildcard auto-approve: Bash(*).claude/settings.jsonScope permissions to specific allowed commands only.

    Next steps

    1. Review the linked incident writeup for the com.anthropic.cl-helper persistence pattern.
    2. Update .mcp.json to include specific version tags for all npx or uvx commands.
    3. Restrict Bash tool permissions to non-destructive, scoped operations.

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

    About this skill

    Coding agents with broad system permissions can unknowingly execute malicious hooks or run unpinned MCP packages. This skill audits your environment for backdoors and risky configurations.

    What it does

    • Detects backdoors by scanning for indicators of the October 2026 Open-VSX incident, including SSH keys and persistence scripts.
    • Identifies risky hooks such as commands that pipe remote downloads to a shell or write to authorized_keys.
    • Audits MCP servers to find unpinned npx or uvx packages that risk supply-chain injection.
    • Flagging broad permissions by highlighting wildcard auto-approval rules like Bash(*) that lack proper scoping.
    • Provides triage levels by returning distinct exit codes for clean, warning, and critical security states.

    How it works

    1. Analyze environment by locating local config files like .mcp.json and .claude/settings.json.
    2. Execute scan using the bundled zero-dependency Python script to check for compromise indicators.
    3. Review findings categorized by severity (Info, Warning, Critical) based on heuristic patterns.
    4. Report results with specific file paths, risk explanations, and suggested one-line fixes.

    Frameworks & tools

    This skill utilizes a standalone Python 3 script with no external dependencies. It targets configurations for Claude Code, Cursor, Claude Desktop, and any environment utilizing the .mcp.json standard.

    Why this beats prompting it yourself

    Generic prompts often miss specific IoCs (Indicators of Compromise) like specialized macOS LaunchAgents or Linux cron patterns used in known attacks. This tool uses a deterministic script to verify system state and config files against a known database of malicious signatures.

    Use cases

    • Post-incident verification to check if a machine was hit by the 2026 extension backdoor.
    • Pre-commit security review of project-level .mcp.json files before sharing with a team.
    • Permission hardening to find and scope overly broad auto-approval rules.
    • Supply-chain auditing to ensure all MCP-based tools use pinned package versions.

    Known limitations

    This is a heuristic triage tool, not a guarantee of safety. It cannot detect zero-day exploits or backdoors that do not follow known persistence patterns.

    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.

    Heuristic-based only. Cannot detect unknown persistence methods. Requires Python 3 to execute the scan script. Does not auto-remediate found issues.

    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

    4.0
    1 review
    5
    0
    4
    1
    3
    0
    2
    0
    1
    0

    This skill has been used 1 time.

    Trust & safety

    Security scan

    Security scan passed 16 days ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Environment Variables
    Listed16 days ago

    What's inside

    Frequently Asked Questions

    This skill scans for specific Indicators of Compromise (IoCs), such as persistence scripts and unauthorized SSH keys, linked to the October 2026 Open-VSX supply-chain incident. It bridges the gap between general AI behavior and low-level system security.

    The tool is designed to audit configurations for Claude Code, Cursor, and Claude Desktop, as well as any environment using the .mcp.json standard for Model Context Protocol servers.

    Unpinned packages (like 'npx package-name' without a version) can be hijacked via supply-chain attacks; this skill identifies these vulnerabilities and provides one-line fixes to pin them to specific, safe versions.

    No, this is a zero-dependency Python script designed for local execution, ensuring your configuration files and security status are never uploaded to a third-party server.

    You receive the standalone Python 3 auditing script, a guide for interpreting severity levels, and a library of heuristic patterns used to detect known backdoors and risky hooks.

    While the skill provides a deterministic scan of known patterns and persistence mechanisms, it is a heuristic triage tool and cannot guarantee protection against zero-day exploits or novel attack vectors.

    New in Security

    Free