# Panguard

> AI agent security platform — audit skills, scan for threats, and run 24/7 protection with 9,700+ detection rules

- **Type:** Skill
- **Install:** `agentstack add skill-panguard-ai-panguard-ai-openclaw-skill`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [panguard-ai](https://agentstack.voostack.com/s/panguard-ai)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [panguard-ai](https://github.com/panguard-ai)
- **Source:** https://github.com/panguard-ai/panguard-ai/tree/main/packages/panguard-mcp/openclaw-skill
- **Website:** https://panguard.ai

## Install

```sh
agentstack add skill-panguard-ai-panguard-ai-openclaw-skill
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Panguard AI — Security for AI Agents

Panguard protects AI agents from prompt injection, tool poisoning, data exfiltration, and 9 other threat categories using 9,700+ detection rules (Sigma + YARA + ATR).

## Available Commands

### Audit installed skills for security threats

```bash
panguard audit skill .
```

Scans all SKILL.md files in the current directory and subdirectories. Reports risk level, flagged patterns, and recommendations.

### Quick security scan

```bash
panguard scan
```

Runs a fast security health check on the current system.

### Full security scan with code analysis

```bash
panguard scan --depth full
```

Deep scan including SAST code analysis, dependency audit, and threat detection.

### Start real-time protection (Guard)

```bash
panguard guard start
```

Starts the Guard engine as a background daemon. Monitors all agent activity in real-time using ATR (Agent Threat Rules), Sigma, and YARA rules.

### Check Guard status

```bash
panguard guard status
```

Shows whether Guard is running, rule counts, and recent alerts.

### Stop Guard

```bash
panguard guard stop
```

### Show system status dashboard

```bash
panguard status
```

Displays a comprehensive status panel: Guard state, rule counts, threat stats, and connected platforms.

### Show recent security alerts

```bash
panguard guard alerts
```

## Workflow

When the user asks about security, skill auditing, or threat protection:

1. If they want to **audit skills**: Run `panguard audit skill ` on the target directory
2. If they want a **security scan**: Run `panguard scan` (add `--depth full` for thorough analysis)
3. If they want **real-time protection**: Run `panguard guard start`
4. If they want **status**: Run `panguard status`

## Setup

If panguard is not installed, install it:

```bash
npm install -g @panguard-ai/panguard
```

Then configure for all AI agent platforms:

```bash
panguard setup
```

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [panguard-ai](https://github.com/panguard-ai)
- **Source:** [panguard-ai/panguard-ai](https://github.com/panguard-ai/panguard-ai)
- **License:** MIT
- **Homepage:** https://panguard.ai

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-panguard-ai-panguard-ai-openclaw-skill
- Seller: https://agentstack.voostack.com/s/panguard-ai
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.