skarn-guard

A security guard for Claude Code that checks tool calls, permission requests, prompts, and new subagents before they run. It also reports possible secret leaks, malicious package installs, and data theft after a response.

In plain words
What is it for?
Reviewing Claude Code activity for exposed credentials, unsafe packages, or data exfiltration. Its audit skill can scan sessions and check assistant configuration, with sensitive values redacted.
Why use it?
It helps you notice risky coding-agent actions before or after they happen. By default it only reports findings; blocking requires enforcement mode and a registered license.

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 skarn-security/agent-guard
agentmods
npx agentmods add plugins/skarn-security/agent-guard/claude
Clone the repo
git clone --depth 1 https://github.com/skarn-security/agent-guard

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

skarn-guard 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 · 20 lines

What it actually says

{
  "name": "skarn-guard",
  "version": "0.27.0",
  "description": "Real-time guard on five Claude Code pre-execution hook events (tool calls, permission decisions, submitted and expanded prompts, and subagent creation) plus a response-end advisory that flags an action leaking a secret, installing a malicious package, or exfiltrating data, plus the skarn-audit skill (scan sessions and vet configs, redacted). Ships in audit mode, which reports the verdict and never changes what the agent does; blocking needs enforce mode and a registered license. Backed by the Skarn detection engine.",
  "author": {
    "name": "Skarn",
    "url": "https://getskarn.com"
  },
  "homepage": "https://getskarn.com",
  "repository": "https://github.com/skarn-security/agent-guard",
  "license": "MIT",
  "keywords": [
    "security",
    "secrets",
    "guard",
    "skills",
    "audit"
  ]
}
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 · 20 lines scan A 6ccf2c94dc05

Subscribe to this mod's changes

skarn-guard is a plugin published in the GitHub repository skarn-security/agent-guard (31 stars, last pushed 4d 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 2026-08-30.