# Staying Safe with goose

> Keep your goose workflows safe with built-in security features and best practices

- 网址：https://funcoding.ai/agents/goose/guides/security/
- 来源：goose 官方文档原文（英文），Apache-2.0 许可，同步于 2026-10-11
- 官方原文：https://goose-docs.ai/docs/guides/security

---
<h1 class={styles.pageTitle}>Staying Safe with goose</h1>
<p class={styles.pageDescription}>
  Understanding security risks and following best practices can help you secure your workflows with goose.
</p>

<div class={styles.categorySection}>
  <h2 class={styles.categoryTitle}>📚 Documentation & Guides</h2>
  <div class={styles.cardGrid}>
- [Adversary Mode](https://funcoding.ai/agents/goose/guides/security/adversary-mode/)：An independent agent reviewer that silently watches tool calls to protect you in case the agent goes rogue.
- [Prompt Injection Detection](https://funcoding.ai/agents/goose/guides/security/prompt-injection-detection/)：Detect and prevent potentially harmful commands before they run.
- [Classification API Specification](https://funcoding.ai/agents/goose/guides/security/classification-api-spec/)：API specification for self-hosting ML-based prompt injection detection endpoints.
  </div>
</div>

<div class={styles.categorySection}>
  <h2 class={styles.categoryTitle}>📝 Featured Blog Posts</h2>
  <div class={styles.cardGrid}>
- [How to Determine If An MCP Server Is Safe](https://goose-docs.ai/blog/2025/03/26/mcp-security)：Before you plug your agent into just any MCP server, here's how to check if it's actually safe.
- [Securing the Model Context Protocol](https://goose-docs.ai/blog/2025/03/31/securing-mcp)：Building secure and capable AI integrations with Model Context Protocol (MCP) at Block.
  </div>
</div>