# guava-guard

> Use this tool when you need to enhance the security of OpenClaw agents at runtime, protecting against potential threats and vulnerabilities. The guava-guard provides a robust defense mechanism, solving problems related to agent security breaches and data protection. It interfaces with OpenClaw agents to monitor and secure their runtime environment, ensuring safe and reliable operation.

Canonical page: https://skillsregistry.net/skills/koatora20-guava-guard  
JSON: https://api.skillsregistry.net/v1/skills/koatora20-guava-guard

## Description

Runtime security guard for OpenClaw agents.

## 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/koatora20-guava-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": "koatora20-guava-guard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/koatora20-guava-guard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/koatora20-guava-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