agentmods.dev

aishield-security-scan

aishield-security-scan is a plugin for Claude Code from lm203688/aishield. Its manifest loads nothing; the 1 skill it bundles cost 99 tokens per session together, scanned A, original, MIT.

A local-first security scanner for MCP servers, AI skills, and agent workspaces. It checks OWASP MCP and agent security risks plus sandbox hardening, and can work offline without executing scanned commands.

In plain words
What is it for?
Use it to scan MCP configurations, skills, and workspaces, or to produce SBOM and SARIF security reports.
Why use it?
It helps identify unsafe tools, configurations, and agent workspaces before they run. Its reports can be used in security and build processes.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

not rated 2repo changed 1mo ago A scan tokens not measured original MIT

Good fit Use it to scan MCP configurations, skills, and workspaces, or to produce SBOM and SARIF security reports.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add lm203688/aishield
/plugin install aishield-security-scan
View source ↗ lm203688/aishield aishield.ai
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/lm203688/aishield

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for aishield-security-scan

README.md
[![agentmods](https://agentmods.dev/badge/plugins/lm203688/aishield/aishield-plugins/github.svg)](https://agentmods.dev/plugins/lm203688/aishield/aishield-plugins)
Your own site
<a href="https://agentmods.dev/plugins/lm203688/aishield/aishield-plugins"><img src="https://agentmods.dev/badge/plugins/lm203688/aishield/aishield-plugins/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for aishield-security-scan

Your own site · 80×15
<a href="https://agentmods.dev/plugins/lm203688/aishield/aishield-plugins"><img src="https://agentmods.dev/badge/plugins/lm203688/aishield/aishield-plugins.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill cost 99 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

aishield-security-scan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

distribution/aishield-plugins/.claude-plugin/plugin.json · 37 lines

What it actually says

{
  "$schema": "https://www.anthropic.com/schema/plugin.json",
  "name": "aishield-security-scan",
  "version": "4.11.0",
  "description": "AIShield security scanner for MCP servers, AI Skills, and agent workspaces. Covers OWASP MCP Top 10 + OWASP Agentic AI Top 10 + sandbox hardening. Zero-dependency, local-first, offline-capable.",
  "author": {
    "name": "lm203688",
    "url": "https://github.com/lm203688/aishield"
  },
  "homepage": "https://aishield.tools",
  "repository": "https://github.com/lm203688/aishield",
  "license": "MIT",
  "keywords": [
    "security",
    "scanner",
    "mcp",
    "agent",
    "skill",
    "prompt-injection",
    "supply-chain",
    "sbom",
    "sarif"
  ],
  "categories": [
    "quality-security"
  ],
  "mcpServers": {
    "aishield": {
      "command": "npx",
      "args": ["-y", "aishield-mcp-server"],
      "description": "AIShield security scanner as an MCP server — scan MCP configs, AI Skills, and agent workspaces without ever executing a scanned command."
    }
  },
  "skills": ["skills/aishield-security-scan/SKILL.md"],
  "readme": "README.md"
}
Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 99 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago Changed 56bc169a3c83
  2. 1mo ago Changed cf24bbe95f8b
  3. 1mo ago Changed 1cc5185c232a
  4. 1mo ago Changed 633bb283998c
  5. 1mo ago First seen · 37 lines scan A aaf492a0b38c

Subscribe to this mod's changes

aishield-security-scan is a plugin published in the GitHub repository lm203688/aishield (2 stars, last pushed 12d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-22.

Building agentsPrompt InjectionSecurityai-agentmcpmcp-server
Related

aishield-security-scan compared with plugins from other repositories

aishield-security-scan next to 6 plugins from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
aishield-security-scanlm203688/aishieldPlugin212d agoMITA—Claude Code
secedgar-mcp-servercyanheads/secedgar-mcp-serverPlugin12yesterdayApache-2.0A—Claude Code
servosityServosity/msp-skillsPlugin79yesterdaynoneA—Claude Code
kadamkadam-official/mcp-serverPlugin018d agoMITA—Cursor
linkedctlalexey-pelykh/linkedctlPlugin24d agoAGPL-3.0A—Claude Code
wikimothjuliangeymonat-jpg/wikimothPlugin84mo agoApache-2.0A—Claude Code
youtube-outlier-researchAdesiaHQ/bangermap-integrationsPlugin03mo agoMITA—Claude Code