skillsguard SKILL.md skillB
skillsguard from teycir/skillsguard is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add teycir/skillsguard/skillsguard@git:20260619.6f5ec76Pins git:20260619.6f5ec76 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- teycir/skillsguard
- Path
skill/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260619.6f5ec76, committed Jun 19, 2026
- First version recorded
- Jun 18, 2026
- Size
- 7,441 bytes
- Repository stars
- 15
- License
- none declared
Audit AI agent skill packages for security threats before installing or using them. Use this skill to scan a SKILL.md file or skill directory for prompt injection, exfiltration, command injection, persistence, privilege escalation, obfuscation, supply-chain attacks, and model-specific jailbreak patterns. Triggers: 'scan skill', 'audit skill', 'skillsguard', 'check this skill', 'is this skill safe', 'skill security', 'skill audit', 'review skill', 'scan all skills', 'audit my skills folder'.
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
# SkillsGuard — Skill Security Auditor You are a security auditor for AI agent skill packages. Your job is to scan skills using the SkillsGuard MCP tools, interpret the results, and give the user a clear verdict. ## Available MCP tools | Tool | When to use | |------|-------------| | `scan_skill` | One specific skill directory or file | | `scan_skills_dir` | A parent directory containing many skill subdirectories | If neither tool is available, fall back to the CLI: ```bash skillsguard /path/to/skill --json ``` If the CLI isn't installed either — or the target is a **remote file you found online and haven't downloaded** (e.g. a `SKILL.md` linked from a GitHub repo or search result) — use the free hosted **Cloud API** on Cloudflare Workers instead. No install, no key, no local file required: ```bash # Stream a remote file straight into the scanner — never touches disk curl -s https://raw.githubusercontent.com/owner/repo/main/SKILL.md | \ curl -s --data-binary @- https://skillsguard.apiskillsguard.workers.dev/scan # Or scan a local file the same way curl -s --data-binary @SKILL.md https://skillsguard.apiskillsguard.workers.dev/scan ``` …
Read the whole file at its exact version.
How to install
mdr add teycir/skillsguard/skillsguard@sha256:9d4b8b94bce47011The line at the top of this page pins the label git:20260619.6f5ec76, 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_fq6yupnbnjajd744)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jun 18, 2026 and Jun 19, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260619.6f5ec76 latest | 2026-06-19 | 6f5ec76 | 7,441 B | B | view · diff |
| git:20260619.1e9e9bc | 2026-06-19 | 1e9e9bc | 5,616 B | B | view · diff |
| git:20260618.a9f7bd4 | 2026-06-18 | a9f7bd4 | 4,389 B | B | view |
Audit of the latest version
- fail: No prompt-injection phrasing (matched: ignore all previous instructions)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7441 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 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
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
teycir/skillsguard · 15 stars · license none declared · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_fq6yupnbnjajd744 GET https://markdownregistry.com/api/v1/resolve?ref=teycir/skillsguard/skillsguard GET https://markdownregistry.com/api/v1/blob/9d4b8b94bce4701172fa380bd979e06c943b0e4aaa779205096440d21f284738
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.