# genpark-agent-bash-command-sandbox-guard-skill

> genpark-agent-bash-command-sandbox-guard-skill — alphaparkinc-genpark-agent-bash-command-sandbox-guard-skill. Use this tool when you need to safeguard your system from potentially destructive bash commands, and ensure secure execution of scripts by blocking harmful system mutations, path traversals, and reverse shells. It analyzes bash commands using AST and heuristics, providing a reliable defense mechanism without relying on external dependencies. Ideal for use cases involving automated script execution, such as git workflows, to prevent unintended system modifications.

Canonical page: https://skillsregistry.net/skills/alphaparkinc-genpark-agent-bash-command-sandbox-guard-skill  
JSON: https://api.skillsregistry.net/v1/skills/alphaparkinc-genpark-agent-bash-command-sandbox-guard-skill

## Description

Zero-dependency AST & heuristic bash command sandbox guard blocking destructive system mutations, path traversals, and reverse shells.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/alphaparkinc/genpark-agent-bash-command-sandbox-guard-skill)

## 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": "alphaparkinc-genpark-agent-bash-command-sandbox-guard-skill"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/alphaparkinc-genpark-agent-bash-command-sandbox-guard-skill` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/alphaparkinc-genpark-agent-bash-command-sandbox-guard-skill/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