Search

Prompt injection & tool call security middleware for agentic LLM systems

LLM & Agent Red Teaming Framework — automated security testing for AI systems

Multi-Agent collaborative code review and security scanning system powered by MiMo

Python wrapper for the promptfoo CLI - LLM testing, red teaming, and security evaluation

Reins — runtime security and policy enforcement for Claude Code, OpenClaw, and other AI agents.

Secure, self-hosted personal AI agent with per-tool container isolation

Python library to secure AI agents with environment credentials from multiple secret providers and more

The flight recorder for AI agents - observability and security for Claude Code, Aider, AutoGPT and more

Security setup wizard for OpenClaw - block sensitive files from AI agent access

Runtime security SDK for AI agents — guard tool calls in 1 line

AI Agent Security Monitor — intercept and approve dangerous commands in real-time

Self-hosted AI agent framework. Voice-first. Security-native. No lock-in.

LangChain-compatible tools for weather, crypto, security, memory and more — works with any LangChain agent

IronClaw AI Agent Framework for Android Termux — Zero Trust, secure-by-default

x402 Payment Firewall SDK - On-chain security for autonomous agent payments on Cronos

Execution security for Python AI agents — seatbelt for LangChain, CrewAI, and plain Python.

AgentVerus skill trust scanner — security and behavioral analysis for AI agent skills

A security boundary for LLM agents — policy, audit, and rollback for every tool call

This project enables users to **generate SQL queries from natural language** using **LLM** of their choice while enforcing **Role-Based Access Control (RBAC)** and **Row-Level Security (RLS)**. It also includes **SQL injection detection** and **sensitive data logging** for compliance and security.

Security audit CLI for AI agent skills — scans 10 dimensions with 109 rules