superagent

项目介绍

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.

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

Remove PII, PHI, and secrets from text automatically.

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

Run red team scenarios against your production agent. (Coming soon)

Sign up at superagent.sh to get your API key.

Run Guard on your own infrastructure. No API calls, no data leaving your environment.