Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    agent attack surface review

    1

    Audits AI agent configurations and MCP servers for security risks, secret exposure, and tool overreach.

    $15

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    agent attack surface review

    agent attack surface review

    Example session with this skill installed

    Audit my current Claude Code and MCP setup for security risks. The agent is intended for local refactoring only. Check mcp.json and my project rules for any overreach.

    • Read your context and instructions
    • Compiled the agent attack surface

    I have completed the security review for your Claude Code setup. The audit focused on your project root and the local mcp.json configuration.

    Agent Attack Surface Review

    Scope

    • Agent under review: Claude Code
    • Boundary: Project root (/workspaces/project-alpha) and ~/Library/Application Support/Claude/config.json
    • Intent: Local code refactoring and linting.
    • Exclusions: External CI/CD pipelines and cloud provider IAM roles.

    Verdict: ACCEPTABLE WITH FIXES
    The agent has broad read/write access to the local filesystem but lacks an approval gate for shell execution.

    Surface Summary

    • Tools/MCP Servers: 4 (Filesystem, Shell, Google Search, SequentialThinking)
    • Ingress Channels: 2 (Terminal input, Web search results)
    • Approval Gates: 1 (Write-access only)

    Findings

    • AS-04 | Unsupervised high-impact action | Severity: High
      • Evidence: mcp.json:12 - "shell": {"allow_all": true}
      • Impact: Untrusted input from web search could trigger arbitrary command execution without a prompt.
      • Fix: Change to an allowlist of specific commands or enable auto_approve: false for the shell tool.
    • AS-01 | Secret exposure | Severity: Medium
      • Evidence: .cursor/rules/main.md:45 - export GITHUB_TOKEN=ghp_a1b2...
      • Impact: The token is visible in the agent's context window and could be exfiltrated.
      • Fix: Move the token to a .env file and add it to .gitignore.

    Patch Plan

    • P0: Disable allow_all in mcp.json and move the GitHub token to environment variables.
    • P1: Add an explicit tool allowlist to the agent instructions.

    Unverified

    • I could not verify if the SequentialThinking tool has internal logging enabled. Check the server source code for audit trail implementation.
    {
      "agent": "claude-code",
      "verdict": "ACCEPTABLE WITH FIXES",
      "critical_findings": 0,
      "high_findings": 1,
      "remediation_status": "pending"
    }
    

    Next steps

    • Review the mcp.json file to restrict shell tool permissions.
    • Run scripts/scan_surfaces.py again after moving your secrets to verify redaction.
    • Request a remediation diff if you want me to generate the updated configuration files.

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

    About this skill

    AI agents with autonomous tool access introduce significant security risks, from secret exposure to unsupervised high-impact actions. This skill audits your agent configurations to identify where untrusted input can reach sensitive tools or credentials. It provides a structured, evidence-backed security review for coding agents, MCP servers, and custom agentic runtimes.

    What it does

    • Inventory surfaces by mapping all tools, skills, and MCP servers the agent can invoke and their specific capabilities.
    • Trace reach to identify every file, repository, and database the agent can touch through its toolset.
    • Identify ingress paths where untrusted content like web pages or PR comments could trigger prompt injection.
    • Audit controls by checking for human approval gates, sandboxes, rate limits, and logging.
    • Rank risks across eight security classes including tool overreach and data exfiltration.

    How it works

    1. Define scope by specifying the agent runtime, project root, and the intended purpose of the agent.
    2. Run inventory using the internal scanner to map config surfaces, authority, and reach.
    3. Analyze risks against the severity rubric, checking for unapproved high-impact paths.
    4. Generate report including a security verdict, evidence-backed findings, and a prioritized patch plan.

    Frameworks & tools

    Works with Claude Code, Cursor, Codex CLI, OpenClaw, OpenCode, and custom agent runtimes. Audits mcp.json, CLAUDE.md, AGENTS.md, .cursor/rules, and SKILL.md configurations.

    Why this beats prompting it yourself

    Generic security prompts often miss hidden execution paths in nested MCP configurations or fail to map how ingress data flows into tools. This skill uses a systematic eight-class risk catalog and a dedicated scanner to ensure no surface is skipped. It enforces evidence rules that require specific file paths and line numbers, preventing vague or hallucinated security claims.

    Use cases

    • Pre-shipment audit of a new coding agent before allowing it access to a private repository.
    • MCP hardening to ensure a local server doesn't provide unverified network or shell access.
    • Credential hygiene to find and redact secrets accidentally committed to agent instruction files.
    • Permission review when upgrading an agent's authority to include write or spend capabilities.

    Known limitations

    Does not perform live penetration testing, external host scanning, or compliance certification. Audit is strictly read-only and limited to the local project root and user-level MCP configs.

    Read-only audit of local config files and project root only. No live penetration testing or external network scanning. Scope limited to provided project files and MCP settings.

    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

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 23 days ago

    Requires

    @scope/server
    Node.js

    Permissions

    Terminal / Shell
    Read Files

    Read-only. The skill reads agent config and instruction files inside the declared scope, then reports findings. It does not modify files, run project code, install packages, or send data anywhere. The optional scanner also only reads files and redacts secret values in its output.

    Listed25 days ago
    Updated23 days ago

    What's inside

    Frequently Asked Questions

    The skill audits popular coding environments like Cursor and Claude Code, along with any custom agent runtime that uses MCP (Model Context Protocol) or configuration files like CLAUDE.md and .cursor/rules.

    Unlike generic prompts, this skill uses a specialized scanner to map nested execution paths and requires evidence-backed findings (like specific line numbers) to prevent hallucinations. It follows a structured eight-class risk catalog to ensure no hidden tool overreach or data exfiltration paths are missed.

    No, the audit is strictly read-only and local; it analyzes your configuration files and project root to identify vulnerabilities without executing tools or performing live penetration tests.

    You receive the core auditing logic, the eight-class risk rubric, and a reporting template that generates prioritized patch plans and evidence-backed security verdicts.

    It is ideal for pre-shipment audits before granting agents access to private repositories, hardening MCP servers against unauthorized shell access, and identifying hardcoded secrets in agent instruction files.

    New in LLM Ops