# agent-skill-guard

> agent-skill-guard — norbilukacs-agent-skill-guard. Use this tool when you need to secure your AI agent skills from hidden threats, such as Unicode prompt injection and data exfiltration. The agent-skill-guard audits your skills to catch vulnerabilities that markdown-only vetters may miss, providing a safer interface for your AI agents. It integrates with git, allowing for seamless security checks and outputs alerts for potential security risks.

Canonical page: https://skillsregistry.net/skills/norbilukacs-agent-skill-guard  
JSON: https://api.skillsregistry.net/v1/skills/norbilukacs-agent-skill-guard

## Description

Security auditor for AI agent skills — catches hidden-Unicode prompt injection, reviewer-subversion, data exfiltration & post-install drift that markdown-only vetters miss.

## Trust

- **Trust score (0–1):** 0.96
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/NorbiLukacs/agent-skill-guard)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "norbilukacs-agent-skill-guard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/norbilukacs-agent-skill-guard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/norbilukacs-agent-skill-guard/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt