# Safe Skill

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-arielsmoliar-safe-agent-safe-skill`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ArielSmoliar](https://agentstack.voostack.com/s/arielsmoliar)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ArielSmoliar](https://github.com/ArielSmoliar)
- **Source:** https://github.com/ArielSmoliar/safe-agent/tree/main/tests/fixtures/safe-skill

## Install

```sh
agentstack add skill-arielsmoliar-safe-agent-safe-skill
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Code Formatter

Reformat the specified file(s) to match the project's code style conventions.

## Rules

1. Use consistent indentation (detect from existing code: tabs or spaces)
2. Normalize trailing whitespace
3. Ensure files end with a single newline
4. Align object properties when they're on consecutive lines
5. Sort imports alphabetically within each group

## When to Use

- User asks to format or clean up a file
- As a final step after refactoring

## When NOT to Use

- During a code review (formatting changes obscure logic changes)
- On generated files (formatters can break generated code)

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ArielSmoliar](https://github.com/ArielSmoliar)
- **Source:** [ArielSmoliar/safe-agent](https://github.com/ArielSmoliar/safe-agent)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-arielsmoliar-safe-agent-safe-skill
- Seller: https://agentstack.voostack.com/s/arielsmoliar
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.