AgenShield — AI Agent Security Platform

AI agent security scanner and npm audit for MCP servers, Claude Code, Cursor, and Windsurf. Find prompt injection, hallucinated packages, secrets, unsafe tools, and vulnerable code.

Multi-engine AI agent security scanner — one scan, four engines, one report

Framework-agnostic agent security gateway — protect any AI agent with Veridex security packs, regardless of framework

Open-source agent security framework. Detects and defends against AI Agent Traps - content injection, embedded jailbreaks, RAG poisoning, data exfiltration, and more.

Command-line tool to manage the Agent Security Gateway

Provider-neutral adversarial conformance for agent security plus A2A, MCP, Arazzo, and WebMCP standards.

AI agent security plugin for OpenClaw: prompt injection detection, PII sanitization, and monitoring dashboard

Canonical schemas and TypeScript types for the Dadieng agent security protocol.

Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1700+ vulnerability rules with AST & taint analysis, LLM-powered semantic code review, auto-fix. For Claude Code, Cursor, Windsu

Ory Agent Security for the OpenRouter Agent SDK - per-tool authorization, activity auditing, and session identity via lifecycle hooks. Built on @ory/argus.

Stew Code — Terminal coding agent. Security Scanner, Self-Verify, Endurance Mode, Skill Forge, Dev Environment Setup, 16+ skills. Zero deps.

Core SDK for Adrian multi-agent security monitoring in Node.js.

AI-powered multi-agent security platform. 29 agents scan 80+ attack classes including AI integration supply chain (Vercel-class attacks), Hermes Agent deployment scanning (ASI-01–ASI-10), tool registry poisoning, function-call injection, skill permission

Ory Agent Security for the Vercel AI SDK — per-tool authorization, activity auditing, and identity propagation by wrapping tool execute(). Built on @ory/argus.

Ory Agent Security for Mastra — per-tool authorization, activity auditing, and identity propagation via agent tool-call hooks (or wrapping tool execute). Built on @ory/argus.

TypeScript SDK for the Argus multi-agent security consensus oracle on Arc

AI agent security proxy — intercepts MCP tool calls in real time

Ory Agent Security for the Anthropic Claude Agent SDK — per-tool authorization, activity auditing, and identity propagation via PreToolUse hooks and canUseTool. Built on @ory/argus.

Agent security runtime for Node.js and browsers: provenance-tracked tool-call guard (CaMeL-style), spotlighting, fuzzy canaries, and hybrid rules + embedded ML detection for prompt injection. Zero dependencies, TypeScript-first, published benchmarks.