agentguards-claude

A security plugin for Claude Code that checks for jailbreaks, prompt injection, unsafe web content, data theft, and unauthorized destructive commands. It includes a security server and enforcement hooks.

In plain words
What is it for?
Use it to scan prompts and web content, block data exfiltration, detect jailbreak attempts, and require authorization for destructive actions.
Why use it?
It adds checks around agent instructions, web content, sensitive data, and risky commands before they can cause harm.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add alelaguard/agentguards-plugins
agentmods
npx agentmods add plugins/alelaguard/agentguards-plugins/claude
Clone the repo
git clone --depth 1 https://github.com/alelaguard/agentguards-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

agentguards-claude 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 yesterday.

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.

claude/.claude-plugin/plugin.json · 23 lines

What it actually says

{
  "name": "agentguards-claude",
  "displayName": "AgentGuards",
  "description": "LLM security guardrails for Claude Code — jailbreak detection, prompt-injection and web-content scanning, data-exfiltration blocking, and destructive-command authorization. Bundles the AgentGuards MCP server plus enforcing hooks.",
  "version": "0.2.30",
  "author": {
    "name": "AgentGuards",
    "email": "[email protected]",
    "url": "https://agentguards.co"
  },
  "homepage": "https://agentguards.co",
  "repository": "https://github.com/alelaguard/agentguards-plugins",
  "license": "MIT",
  "userConfig": {
    "agentguards_api_key": {
      "type": "string",
      "title": "AgentGuards API key",
      "description": "Optional fallback for the hooks when AGENTGUARDS_API_KEY is not already set. The easiest way to set your key is to run /agentguards:setup in an Agent Mode or Local Code session and let Claude save it for you. Note the Claude Desktop app never reads a shell profile, so an export will not reach it.",
      "sensitive": true
    }
  }
}
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. yesterday First seen · 23 lines scan A 0ed86a5cc2a1

Subscribe to this mod's changes

agentguards-claude is a plugin published in the GitHub repository alelaguard/agentguards-plugins (1 stars, last pushed 2d 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 2026-08-31.