---
name: "Gate agent inputs and outputs with Superagent safety checks"
slug: "gate-agent-inputs-and-outputs-with-superagent-safety-checks"
description: "Use Superagent to add prompt-injection blocking, PII redaction, repository scanning, and compliance evidence around AI agent runs."
github_stars: 6615
verification: "listed"
source: "https://github.com/superagent-ai/superagent"
author: "Superagent AI"
publisher_type: "open_source_project"
category: "Security & Verification"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "superagent-ai/superagent"
  github_stars: 6615
  npm_package: "safety-agent"
  npm_weekly_downloads: 43707
---

# Gate agent inputs and outputs with Superagent safety checks

Use Superagent to add prompt-injection blocking, PII redaction, repository scanning, and compliance evidence around AI agent runs.

## Prerequisites

Superagent SDK, CLI, or MCP server; SUPERAGENT_API_KEY for hosted checks or supported local guard model

## Installation

No source-backed install or usage instructions could be extracted automatically. Review the upstream project before running this skill in a sensitive workflow.

- Source: https://github.com/superagent-ai/superagent

## Documentation

- https://docs.superagent.sh

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/gate-agent-inputs-and-outputs-with-superagent-safety-checks/)