Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    agent shield

    1

    Perform evidence-based security audits and risk scoring for AI agents, MCP tools, and system prompts.

    Free

    Security scanned
    agent shield

    agent shield

    Example session with this skill installed

    Perform a security preflight on this MCP tool definition for a local file-search agent. It has read access to the home directory and uses a recursive search function.

    • Read your context and instructions
    • Compiled the agent shield

    I have completed the security preflight for the file-search MCP tool.

    Executive Verdict

    • Security Score: 72/100
    • Overall Risk: High
    • Audit Confidence: 85%
    • Recommendation: Do not deploy without restricting the root search path.

    Security Findings

    IDSeverityFindingImpactPenalty
    AS-001HighExcessive Directory PermissionsSensitive file exposure7
    AS-002MediumRunaway RecursionResource exhaustion/DDoS3
    AS-003LowMissing Search BoundariesInformation leakage1

    Failure Path

    1. Injection: An untrusted prompt asks the agent to search for .ssh/id_rsa.
    2. Execution: The agent uses the recursive_search tool starting from the home directory.
    3. Exfiltration: The tool successfully reads and returns private key contents to the LLM context.

    Fix Pack

    • Current Problem: Tool allows searching from ~/ which includes sensitive credentials.
    • Recommended Change: Hardcode the search root to a specific project directory or use an allowlist.
    • Safe Example: const SEARCH_ROOT = '/home/user/projects/current';

    Next steps

    • Implement a search directory allowlist to prevent access to hidden system folders.
    • Add an action limit or depth cap to the recursive search function to prevent runaway loops.
    • Review the Residual Risk section regarding missing network egress logs.

    Score Calculation

    Starting score: 100
    Finding penalties: -11
    Control bonus: +0
    Final Security Score: 72/100
    Audit Confidence: 85%
    

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

    About this skill

    AI agents often ship with over-privileged tools, hidden prompt injection vectors, and runaway autonomy that leads to high compute costs or data leaks. Agent Shield provides an evidence-based security preflight for AI agents, MCP configurations, and agentic workflows. It identifies critical weaknesses before you deploy or publish.

    What it does

    • Vulnerability Analysis checks for prompt injection, goal hijacking, and tool-description poisoning.
    • Permission Auditing evaluates excessive agency against an intended capability baseline.
    • Supply Chain Review inspects MCP server definitions, tool shadowing, and dependency risks.
    • Risk Scoring generates a calibrated security score (0-100) based on impact, exploitability, and controls.
    • Remediation Planning provides specific failure paths, recommended fixes, and verification steps.

    How it works

    1. Analyze Material by reviewing the agent's instructions, tool definitions, and permission policies.
    2. Establish Baseline by determining what the agent actually needs to accomplish its purpose.
    3. Execute Domains across 10 security categories including memory, network, and autonomy.
    4. Calculate Scores using a mathematical penalty model and audit confidence metric.

    Frameworks & tools

    Works with any agentic architecture including Claude Code, Cursor rules, MCP (Model Context Protocol) servers, and custom tool-calling agents.

    Why this beats prompting it yourself

    Generic security prompts often hallucinate vulnerabilities or miss the nuance of agent autonomy. Agent Shield uses a strict evidence standard and a mathematical scoring system to ensure findings are objective, deduplicated, and actionable.

    Use cases

    • Pre-deployment Audit of new MCP tools or agentic skills before company-wide rollout.
    • Prompt Hardening to identify injection vectors in complex multi-step instructions.
    • Permission Scoping to ensure coding agents have appropriate filesystem and network access.
    • Cost Control Review to detect potential runaway loops and unbounded tool execution.

    Known limitations

    This is a static security review aid, not a runtime penetration test or a guarantee of safety. It cannot verify implementation details that are not provided in the supplied documentation or code.

    Static assessment only. No runtime testing. Does not certify compliance. Results depend entirely on the quality of supplied material.

    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 28 days ago

    • Free with an Agensi account

    Permissions

    Network Access
    Listed28 days ago
    Updated2 days ago

    What's inside

    Frequently Asked Questions

    Agent Shield identifies vulnerabilities like prompt injection and over-privileged permissions, providing a 0-100 risk score and specific remediation steps to prevent data leaks and runaway compute costs.

    It is designed to be framework-agnostic, supporting any agentic architecture including Claude Code, Cursor rules, and Model Context Protocol (MCP) server definitions.

    No complex installation is required; simply provide the agent's instructions, tool definitions, or permission policies to the skill to initiate a comprehensive security preflight.

    You receive the full vulnerability analysis framework, the mathematical risk-scoring model, and a structured remediation template to ensure your findings are objective and actionable.

    While it identifies potential runaway loops and unbounded tool execution vectors, it is a static audit tool and does not provide real-time runtime monitoring or firewall capabilities.

    New in LLM Ops