panguard-skill-auditor SKILL.md skillC
panguard-skill-auditor from panguard-ai/panguard-ai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add panguard-ai/panguard-ai/panguard-skill-auditor@git:20260312.b920a35Pins git:20260312.b920a35 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- C, 15 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- panguard-ai/panguard-ai
- Path
skills/panguard-skill-auditor/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260312.b920a35, committed Mar 12, 2026
- First version recorded
- Mar 6, 2026
- Size
- 5,214 bytes
- Repository stars
- 67
- License
- MIT
Automated security auditor for AI agent skills. Scans SKILL.md files for prompt injection, tool poisoning, hidden Unicode, encoded payloads, secrets, and dangerous permissions. Returns a 0-100 risk score.
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 Skill Auditor
Automated security scanner for AI agent skills. Use **before installing any skill** from ClawdHub, GitHub, or other sources.
Unlike manual checklists, this runs real static analysis: regex pattern matching, Unicode inspection, Base64 payload decoding, SAST, and secrets scanning.
## When to Use
- Before installing any skill from ClawdHub or GitHub
- When evaluating third-party SKILL.md files
- Before adding skills to your agent fleet
- As a CI gate for skill repositories
## Quick Start
```bash
# Audit a skill directory
panguard audit skill ./path/to/skill
# Audit a skill from a GitHub URL
panguard audit skill https://github.com/user/repo/tree/main/skills/my-skill
```
## What It Checks
### 1. Manifest Validation
Verifies SKILL.md frontmatter: required fields (name, description), valid metadata structure, and proper formatting.
### 2. Prompt Injection Detection
11 regex patterns detect:
- "Ignore previous instructions" variants
- Identity override ("you are now", "act as")
- System prompt manipulation
- Jailbreak patterns (DAN, bypass safety)
- Hidden text in HTML/markdown comments
### 3. Hidden Content Detection
…Read the whole file at its exact version.
How to install
mdr add panguard-ai/panguard-ai/panguard-skill-auditor@sha256:40c1f6f860aa899cThe line at the top of this page pins the label git:20260312.b920a35, 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.
[](https://markdownregistry.com/a/art_mdkjxarzzmtf5aoa)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Mar 6, 2026 and Mar 12, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260312.b920a35 latest | 2026-03-12 | b920a35 | 5,214 B | C | view · diff |
| git:20260312.0dc8494 | 2026-03-12 | 0dc8494 | 4,941 B | C | view · diff |
| git:20260306.9e15e22 | 2026-03-06 | 9e15e22 | 4,941 B | C | view |
Audit of the latest version
- fail: No prompt-injection phrasing (matched: Ignore previous instructions)
- fail: No curl or wget piped into a shell (matched: curl -fsSL https://panguard.ai/api/install | bash)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5214 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 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
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
panguard-ai/panguard-ai · 67 stars · license MIT · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_mdkjxarzzmtf5aoa GET https://markdownregistry.com/api/v1/resolve?ref=panguard-ai/panguard-ai/panguard-skill-auditor GET https://markdownregistry.com/api/v1/blob/40c1f6f860aa899ce79a7accfd10044b7038a5aeb7e67e8b58b618186f44305d
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.