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.
git clone --depth 1 https://github.com/lm203688/aishieldWrote 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.
[](https://agentmods.dev/plugins/lm203688/aishield/aishield-plugins)<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.
<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>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 today.
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.
What it actually says
{
"$schema": "https://www.anthropic.com/schema/plugin.json",
"name": "aishield-security-scan",
"version": "4.3.0",
"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"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 91 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
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.
- today First seen · 37 lines scan A aaf492a0b38c
aishield-security-scan is a plugin published in the GitHub repository lm203688/aishield (2 stars, last pushed today), 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.
Other plugins, from other repositories
secedgar-mcp-server
Query SEC EDGAR filings, XBRL financials, and company data through MCP. STDIO & Streamable HTTP.
verychic-mcp
Browse VeryChic flash-sale hotel deals from any MCP client. Filter offers by destination, price, discount, stars, theme or proximity, and look up prices and availability by date. Read-only and anonymous, no account needed. Unofficial, not affiliated with VeryChic.
safe-android-reverser
Sandboxed Android reverse engineering with semantic program indexing, XREF/CFG queries and structured network evidence through MCP.
claude-webcache
Cross-session WebFetch cache for Claude Code. WebFetches disappear after 15 minutes — claude-webcache makes them persist.
servosity
The first MSP-fleet CLI for backup. Every Servosity API endpoint as a typed command, plus a local mirror that lets you ask questions the dashboard can't — across your whole book of clients.
wikimoth
Deterministic, token-minimal memory for Claude Code: capture each session as a [[wikilink]] note (edges computed by code, not a model) and recall connected notes at boot.