Search

MCP 工具面安全扫描器（Java）—— 指纹化并锁定 MCP 服务器工具定义，检测 schema 投毒 / 工具影子 / rug pull，可作 CI 门禁

AEAP Composition Boundary Adapter for Google ADK. Thin wrapper that attaches the Runtime Decision Point to agent tool invocations.

Manual Verification Protection + AI Selector Compatible with OpenClaw . This is a complete TypeScript plugin project—a true implementation of the `before_tool_call` hook that can intercept tool calls, follow OpenClaw’s built-in approval workflow, and features an approval window mechanism.

Client-side tool-call gate for coding agents: screens what Claude Code and Codex are about to run, and keeps a tamper-evident record of it.

LLM Security Platform Docs

TrustGuard security integration for CrewAI agents

AI agent behavioral security monitoring SDK

Vaultak runtime security components for Haystack pipelines

AI Agent CLI Security Sandbox for Docker and Podman

Static security scanner for LLM and AI-agent applications.

Local-first security runtime for AI coding agents

MCP security wrapper with policy tiers, approvals, backup, and audit.

ArmorClaw intent enforcement and security plugin for OpenClaw AI agents

Autonomous Offensive Security Intelligence - AI-powered penetration testing

LangChain integration for LatchGate — execution security kernel for AI agents

CrewAI integration for LatchGate — execution security kernel for AI agents

Runtime protection and security monitoring for AI agents — The CrowdStrike for AI Agents

Keel — an intent-aware security layer for LLM prompts and agent actions.

oktsec plugin for OpenClaw - runtime security for AI agent tool calls

Explainable data-flow security analysis for AI-powered GitHub workflows.