How do I install the Agent Shield skill?

Run npx skillmds@latest add dvcrn/agent-shield-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Agent Shield safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: CAUTION, Skill Scanner: PASS. Capability flags: makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Agent Shield?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Agent Shield free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Agent Shield?

dvcrn (@dvcrn) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Agent Shield by dvcrn — Agent Skill

Name: Agent Shield
Rating: 4.666666666666667 (3 reviews)
Author: dvcrn

Agent Shield

Scan AI agent skills, MCP servers, and plugins for security vulnerabilities. Use when: user asks to check a skill/plugin for safety, audit security, scan for backdoors/data exfiltration/credential leaks, or evaluate trust of a third-party skill. Triggers: "is this skill safe", "scan for security issues", "audit this plugin", "check for backdoors", "安全扫描", "扫一下安不安全".

dvcrn Updated Sep 9, 2026 32 repo stars

File contents

AgentShield — Security Scanner

Scan any directory for security issues in AI agent skills, MCP servers, and plugins.

Usage

# Basic scan
npx @elliotllliu/agent-shield scan ./path/to/skill/

# Pre-install check (GitHub URL, npm package, or local path)
npx @elliotllliu/agent-shield install-check https://github.com/user/repo

# JSON output for programmatic use
npx @elliotllliu/agent-shield scan ./path/to/skill/ --json

# Fail if score is below threshold
npx @elliotllliu/agent-shield scan ./path/to/skill/ --fail-under 70

# Scan .difypkg plugin archives
npx @elliotllliu/agent-shield scan ./plugin.difypkg

What It Detects (30 rules)

High Risk:

data-exfil — reads sensitive files + sends HTTP requests
backdoor — eval(), exec(), dynamic code execution
reverse-shell — outbound socket to shell
crypto-mining — mining pool connections
credential-hardcode — hardcoded API keys/tokens
obfuscation — base64+eval, hex strings
prompt-injection — 55+ patterns, 12 categories, 8 languages
tool-shadowing — tool name/description manipulation
attack-chain — multi-step kill chain (5 stages)
cross-file — cross-file data flow and code injection
ast-* — Python AST taint tracking (eval, pickle, SQL injection, SSTI)
multilang-injection — 8-language prompt injection
description-integrity — semantic mismatch between description and code
mcp-runtime — MCP server runtime security issues

Medium Risk:

env-leak — process.env exfiltration
network-ssrf — user-controlled URLs, SSRF
privilege — SKILL.md permission vs code mismatch
supply-chain — known CVEs in dependencies
sensitive-read — SSH keys, AWS creds access
phone-home — periodic beacon/heartbeat pattern
python-security — 35 Python-specific patterns

Low Risk:

excessive-perms — too many permissions declared
hidden-files — .env with secrets committed
typosquatting — suspicious npm package names

Interpreting Results

Score 90-100: Low risk ✅
Score 70-89: Moderate risk — review warnings
Score 40-69: High risk — investigate before using
Score 0-39: Critical risk — do not install

When to Use

Before installing a third-party skill: npx @elliotllliu/agent-shield install-check <url>
Auditing your own skills before publishing
CI/CD pipeline gate: --fail-under 70
Reviewing skills from untrusted sources

---name: agent-shield-2description: Scan AI agent skills, MCP servers, and plugins for security vulnerabilities. Use when: user asks to check a skill/plugin for safety, audit security, scan for backdoors/data exfiltration/credential leaks, or evaluate trust of a third-party skill. Triggers: "is this skill safe", "scan for security issues", "audit this plugin", "check for backdoors", "安全扫描", "扫一下安不安全".--- # AgentShield — Security Scanner Scan any directory for security issues in AI agent skills, MCP servers, and plugins. ## Usage ```bash # Basic scan npx @elliotllliu/agent-shield scan ./path/to/skill/ # Pre-install check (GitHub URL, npm package, or local path) npx @elliotllliu/agent-shield install-check https://github.com/user/repo # JSON output for programmatic use npx @elliotllliu/agent-shield scan ./path/to/skill/ --json # Fail if score is below threshold npx @elliotllliu/agent-shield scan ./path/to/skill/ --fail-under 70 # Scan .difypkg plugin archives npx @elliotllliu/agent-shield scan ./plugin.difypkg ``` ## What It Detects (30 rules) **High Risk:** - `data-exfil` — reads sensitive files + sends HTTP requests - `backdoor` — eval(), exec(), dynamic code execution - `reverse-shell` — outbound socket to shell - `crypto-mining` — mining pool connections - `credential-hardcode` — hardcoded API keys/tokens - `obfuscation` — base64+eval, hex strings - `prompt-injection` — 55+ patterns, 12 categories, 8 languages - `tool-shadowing` — tool name/description manipulation - `attack-chain` — multi-step kill chain (5 stages) - `cross-file` — cross-file data flow and code injection - `ast-*` — Python AST taint tracking (eval, pickle, SQL injection, SSTI) - `multilang-injection` — 8-language prompt injection - `description-integrity` — semantic mismatch between description and code - `mcp-runtime` — MCP server runtime security issues **Medium Risk:** - `env-leak` — process.env exfiltration - `network-ssrf` — user-controlled URLs, SSRF - `privilege` — SKILL.md permission vs code mismatch - `supply-chain` — known CVEs in dependencies - `sensitive-read` — SSH keys, AWS creds access - `phone-home` — periodic beacon/heartbeat pattern - `python-security` — 35 Python-specific patterns **Low Risk:** - `excessive-perms` — too many permissions declared - `hidden-files` — .env with secrets committed - `typosquatting` — suspicious npm package names ## Interpreting Results - **Score 90-100**: Low risk ✅ - **Score 70-89**: Moderate risk — review warnings - **Score 40-69**: High risk — investigate before using - **Score 0-39**: Critical risk — do not install ## When to Use 1. Before installing a third-party skill: `npx @elliotllliu/agent-shield install-check <url>` 2. Auditing your own skills before publishing 3. CI/CD pipeline gate: `--fail-under 70` 4. Reviewing skills from untrusted sources

Frequently asked questions