Search

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

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

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

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.

Cerberus — Universal Security Skill Book & Specification Engine for AI Agents by Araskova Labs.

Scan Agent Skill packages for security threats using multi-agent AI analysis

AI-powered code review from your terminal — security, performance, and quality agents on every PR

Security-hardened, model-agnostic Python SDK for contract-enforced AI agent workflows

AI agent framework with defense-in-depth security, multi-agent orchestration, and provider abstraction

Security middleware for agentic LLM pipelines: input guard, action guard, and output guard

Evidence-first local security scanner for AI agents, RAG apps, and agent workflows.

Enterprise-grade AI agent engine. Lightweight, secure, MCP-native. Built in Rust.

WALRAXC 13-phase deterministic audit orchestrator — multi-agent security analysis engine

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

Bulwark Vercel AI SDK integration — secure AI tool calls with Bulwark auth

A robust, enterprise-grade, drop-in security & safety guardrail layer for AI agents and LLMs.

Autonomous dual-team (Purple Team) security framework powered by configurable LLM APIs.

A system for compartmentalizing Q CLI projects into secure containers, so the agents can work on the provided data without risk of inadvertently encountering or manipulating other data on the desktop. Agent is pre-provisioned with python, brew, and Perplexity access via an MCP server API key in secure container storage.

This project provides a Docker container for Kali Linux with SSH access, allowing secure remote connections for penetration testing and security research. Additionally, the container includes a terminal-based AI agent and chat tool installed from noxgle/term_agent, providing enhanced AI-assisted interaction within the terminal environment.

Palaryn - Model-agnostic infrastructure layer for AI agent I/O security, cost control, and observability