# Superagent SDK — Guardrails Against Prompt Injection

> Superagent SDK helps protect AI apps: detect prompt injections, redact PII/secrets, scan repos for poisoning, and integrate via TS/Python, CLI, or MCP.

## Install

Paste the prompt below into your AI tool:

## Quick Use

```bash
npm install safety-agent
export SUPERAGENT_API_KEY=your-key
```

```ts
import { createClient } from "safety-agent";
const client = createClient();
const result = await client.guard({ input: userMessage });
if (result.classification === "block") console.log(result.violation_types);
```

## Intro

Superagent SDK is an open-source safety toolkit for agent apps: guard against prompt injections, redact PII/secrets, and scan repos for threats. It offers TS/Python SDKs and a CLI, and is GitHub-verified at 6,594★.

**Best for:** shipping agent apps that need runtime prompt-injection detection and secret/PII redaction

**Works with:** TypeScript/Python SDKs; optional CLI; integrates with Claude Code/Claude Desktop via MCP server (per repo docs)

**Setup time:** 10–25 minutes

### Key facts (verified)

- README lists features: Guard (prompt injection), Redact (PII/secrets), Scan (repo threats).
- README shows install `npm install safety-agent` and environment var `SUPERAGENT_API_KEY`.
- README mentions open-weight guard models with 50–100ms latency (as stated in README).
- GitHub: 6,594 stars · 962 forks; pushed 2026-04-11 (GitHub API verified).

## Main

Add safety guardrails like you add observability:

- Run Guard on every user message and on every tool-call instruction.
- Redact before logging or storing transcripts.
- Use Scan as part of CI for repos that agents can read, to catch repo poisoning patterns.

Start with "report-only" mode (log findings), then switch to blocking once you see false-positive rates in your domain.

### README excerpt (verbatim)

<p align="center">
  <img src="logo.png" width="80" alt="Superagent" />
</p>

<h1 align="center">Superagent SDK</h1>

<p align="center">
  <strong>Make your AI apps safe.</strong>
</p>

<p align="center">
  <a href="https://superagent.sh">Website</a> ·
  <a href="https://docs.superagent.sh">Docs</a> ·
  <a href="https://discord.gg/spZ7MnqFT4">Discord</a> ·
  <a href="https://huggingface.co/superagent-ai">HuggingFace</a>
</p>

<p align="center">
  <img src="https://img.shields.io/badge/Y%20Combinator-Backed-orange" alt="Y Combinator" />
  <img src="https://img.shields.io/github/stars/superagent-ai/superagent?style=social" alt="GitHub stars" />
  <img src="https://img.shields.io/badge/license-MIT-blue" alt="MIT License" />
</p>

---

An open-source SDK for AI agent safety. Block prompt injections, redact PII and secrets, scan repositories for threats, and run red team scenarios against your agent.

## Features

### Guard

Detect and block prompt injections, malicious instructions, and unsafe tool calls at runtime.

**TypeScript:**

```typescript
import { createClient } from "safety-agent";

const client = createClient();

const result = await client.guard({
  input: userMessage
});

if (result.classification === "block") {
  console.log("Blocked:", result.violation_types);
}
```

**Python:**

```python
from safety_agent import create_client

client = create_client()

result = await client.guard(input=user_message)

if result.classification == "block":
    print("Blocked:", result.violation_types)
```

### Redact

Remove PII, PHI, and secrets from text automatically.

**TypeScript:**

```typescript
const result = await client.redact({
  input: "My email is john@example.com and SSN is 123-45-6789",
  model: "openai/gpt-4o-mini"
});

console.log(result.redacted);
// "My email is <EMAIL_REDACTED> and SSN is <SSN_REDACTED>"
```

**Python:**

```python
result = await client.redact(
    input="My email is john@example.com and SSN is 123-45-6789",
    model="openai/gpt-4o-mini"
)

print(result.redacted)
# "My email is <EMAIL_REDACTED> and SSN is <SSN_REDACTED>"
```

### Scan

Analyze repositories for AI agent-targeted attacks such as repo poisoning and malicious instructions.

**TypeScript:**

```typescript
const result = await client.scan({
  repo: "https://github.com/user/repo"
});

console.log(result.result);  // Security report
console.log(`Cost: $${result.usage.cost.toFixed(4)}`);
```

**Python:**

```python
result = await client.scan(repo="https://github.com/user/repo")

print(result.result)  # Security report
print(f"Cost: ${result.usage.cost:.4f}")
```

### FAQ

**Q: Is Superagent open source?**
A: Yes—repo is MIT-licensed per GitHub license metadata.

**Q: How do I install it?**
A: README shows `npm install safety-agent` (and `uv add safety-agent` for Python).

**Q: What does it do?**
A: Guard against prompt injection, redact secrets/PII, and scan repos for threats (per README).

## Source & Thanks

> Source: https://github.com/superagent-ai/superagent
> License: MIT
> GitHub stars: 6,594 · forks: 962

---

<!-- ZH -->

## 快速使用

```bash
npm install safety-agent
export SUPERAGENT_API_KEY=your-key
```

```ts
import { createClient } from "safety-agent";
const client = createClient();
const result = await client.guard({ input: userMessage });
if (result.classification === "block") console.log(result.violation_types);
```

## 简介

Superagent SDK 是开源的 agent 安全工具箱：用于防提示词注入、PII/密钥脱敏，以及仓库威胁扫描。它提供 TS/Python SDK 与 CLI，GitHub 已验证 6,594★。

**最适合：** 需要在运行时检测提示词注入、并对 PII/密钥脱敏的 agent 应用/平台

**适配：** TypeScript/Python SDK；可选 CLI；可通过 MCP 与 Claude 工具链集成（见仓库文档）

**配置时间：** 10–25 分钟

### 关键事实（已验证）

- README 列出核心能力：Guard（注入检测）、Redact（脱敏）、Scan（仓库扫描）。
- README 给出 `npm install safety-agent` 与 `SUPERAGENT_API_KEY` 环境变量。
- README 提到可用开源权重模型在 50–100ms 延迟范围内运行（README 自述）。
- GitHub：6,594 stars · 962 forks；最近更新 2026-04-11（GitHub API 验证）。

## 正文

把安全护栏像可观测性一样接入：

- 对每条用户输入、以及每次工具调用指令都跑 Guard。
- 在日志/存档前先 Redact，避免把 PII/密钥写入系统。
- 对 agent 可读取的仓库，把 Scan 放进 CI，提前发现投毒/恶意指令模式。

建议先以“只报告不拦截”的方式上线，观察误报率后再逐步开启阻断策略。

### README 原文节选（verbatim）

<p align="center">
  <img src="logo.png" width="80" alt="Superagent" />
</p>

<h1 align="center">Superagent SDK</h1>

<p align="center">
  <strong>Make your AI apps safe.</strong>
</p>

<p align="center">
  <a href="https://superagent.sh">Website</a> ·
  <a href="https://docs.superagent.sh">Docs</a> ·
  <a href="https://discord.gg/spZ7MnqFT4">Discord</a> ·
  <a href="https://huggingface.co/superagent-ai">HuggingFace</a>
</p>

<p align="center">
  <img src="https://img.shields.io/badge/Y%20Combinator-Backed-orange" alt="Y Combinator" />
  <img src="https://img.shields.io/github/stars/superagent-ai/superagent?style=social" alt="GitHub stars" />
  <img src="https://img.shields.io/badge/license-MIT-blue" alt="MIT License" />
</p>

---

An open-source SDK for AI agent safety. Block prompt injections, redact PII and secrets, scan repositories for threats, and run red team scenarios against your agent.

## Features

### Guard

Detect and block prompt injections, malicious instructions, and unsafe tool calls at runtime.

**TypeScript:**

```typescript
import { createClient } from "safety-agent";

const client = createClient();

const result = await client.guard({
  input: userMessage
});

if (result.classification === "block") {
  console.log("Blocked:", result.violation_types);
}
```

**Python:**

```python
from safety_agent import create_client

client = create_client()

result = await client.guard(input=user_message)

if result.classification == "block":
    print("Blocked:", result.violation_types)
```

### Redact

Remove PII, PHI, and secrets from text automatically.

**TypeScript:**

```typescript
const result = await client.redact({
  input: "My email is john@example.com and SSN is 123-45-6789",
  model: "openai/gpt-4o-mini"
});

console.log(result.redacted);
// "My email is <EMAIL_REDACTED> and SSN is <SSN_REDACTED>"
```

**Python:**

```python
result = await client.redact(
    input="My email is john@example.com and SSN is 123-45-6789",
    model="openai/gpt-4o-mini"
)

print(result.redacted)
# "My email is <EMAIL_REDACTED> and SSN is <SSN_REDACTED>"
```

### Scan

Analyze repositories for AI agent-targeted attacks such as repo poisoning and malicious instructions.

**TypeScript:**

```typescript
const result = await client.scan({
  repo: "https://github.com/user/repo"
});

console.log(result.result);  // Security report
console.log(`Cost: $${result.usage.cost.toFixed(4)}`);
```

**Python:**

```python
result = await client.scan(repo="https://github.com/user/repo")

print(result.result)  # Security report
print(f"Cost: ${result.usage.cost:.4f}")
```

### FAQ

**Superagent 是开源的吗？**
答：是：GitHub 许可证信息显示为 MIT。

**怎么安装？**
答：README 给出 `npm install safety-agent`（Python 也有 `uv add safety-agent`）。

**主要做什么？**
答：按 README：注入检测、脱敏、仓库威胁扫描等安全能力。

## 来源与感谢

> Source: https://github.com/superagent-ai/superagent
> License: MIT
> GitHub stars: 6,594 · forks: 962


---
Source: https://tokrepo.com/en/workflows/superagent-sdk-guardrails-against-prompt-injection
Author: Prompt Lab