panguard SKILL.md skillA

panguard from panguard-ai/panguard-ai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add panguard-ai/panguard-ai/panguard@git:20260715.6375ea2

Pins git:20260715.6375ea2 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
panguard-ai/panguard-ai
Path
packages/panguard-mcp/openclaw-skill/SKILL.md
Versions recorded
3
Latest version
git:20260715.6375ea2, committed Jul 15, 2026
First version recorded
Mar 11, 2026
Size
2,471 bytes
Repository stars
67
License
MIT

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

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 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
```
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add panguard-ai/panguard-ai/panguard@sha256:8bf5054acb440c1f

The line at the top of this page pins the label git:20260715.6375ea2, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_7odsycruoioobyrm.svg)](https://markdownregistry.com/a/art_7odsycruoioobyrm)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Mar 11, 2026 and Jul 15, 2026, about one every 63 days.

versioncommittedcommitsizeaudit
git:20260715.6375ea2 latest2026-07-15 6375ea2 2,471 BA view · diff
git:20260312.b920a352026-03-12 b920a35 2,484 BA view · diff
git:20260311.9a4e49c2026-03-11 9a4e49c 2,312 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2471 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

panguard-ai/panguard-ai · 67 stars · license MIT · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7odsycruoioobyrm
GET https://markdownregistry.com/api/v1/resolve?ref=panguard-ai/panguard-ai/panguard
GET https://markdownregistry.com/api/v1/blob/8bf5054acb440c1f690a415316fef3f410c0dd9786689716d0f001d9ade0ec21

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from panguard-ai/panguard-ai

DESIGN.md DESIGN.md file
panguard-ai/panguard-ai · DESIGN.md
git:20260407.0b330c0 · audit A · 67 stars
DESIGN.md@packages/website DESIGN.md file
panguard-ai/panguard-ai · packages/website/DESIGN.md
git:20260408.da1735a · audit A · 67 stars
llms-full.txt@packages/website/public llms.txt file
panguard-ai/panguard-ai · packages/website/public/llms-full.txt
git:20261108.5c79362 · audit A · 67 stars
llms.txt@packages/website/public llms.txt file
panguard-ai/panguard-ai · packages/website/public/llms.txt
git:20261016.1750a96 · audit A · 67 stars
panguard-skill-auditor SKILL.md skill
panguard-ai/panguard-ai · skills/panguard-skill-auditor/SKILL.md · Automated security auditor for AI agent skills. Scans SKILL.md files for prompt injection, tool poisoning, hidden…
git:20260312.b920a35 · audit C · 67 stars

Every file in panguard-ai/panguard-ai

Browse by kind, by grade A, or by owner.