# lobsterguard

> Use this tool when you need to identify and fix security vulnerabilities in OpenClaw applications, as it provides 68 checks across 6 categories and 11 auto-fixes, aligned with the OWASP Agentic AI Top 10 standards. It accepts OpenClaw code as input and outputs a detailed audit report with recommendations for remediation. Ideal for use in secure development workflows, particularly when bilingual support is required.

Canonical page: https://skillsregistry.net/skills/jarb02-lobsterguard  
JSON: https://api.skillsregistry.net/v1/skills/jarb02-lobsterguard

## Description

Bilingual security auditor for OpenClaw. 68 checks across 6 categories, 11 auto-fixes, OWASP Agentic AI Top 10.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** security
- **Updated:** 2026-05-18

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/jarb02-lobsterguard)

## 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": "jarb02-lobsterguard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jarb02-lobsterguard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jarb02-lobsterguard/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