JSPM

The Sudo Command for AI Agents. Execution Security for Claude Code & MCP.

Universal AI agent governance — one command to govern Claude, Cursor, Gemini CLI, and OpenCode

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

Cryptographic security layer for AI agents. Ed25519 identity, signed messages, trust scoring. Works with LangChain, CrewAI, AutoGen, OpenClaw, or any agent framework.

AI Agent Governance for TypeScript — policy enforcement, scoring, compliance, and audit for AI agents

Open detection standard for AI agent security. 108 rules for prompt injection, tool poisoning, context exfiltration, and MCP attacks. Shipped in Cisco AI Defense.

AI agent security & MCP security middleware — prompt injection detection, AI firewall, runtime guardrails & data-loss prevention for LLM tool calls. 8-layer defense against data exfiltration & dangerous commands. Zero dependencies. SDK + OpenClaw plugin.

DevFortress SDK — API and application security with automated threat response, session privacy, and AI agent observability.

Security scanner for AI agent tooling — MCP servers, tool definitions, and agentic pipelines

MCPS -- MCP Secure. Drop-in secure replacement for the MCP SDK. ECDSA message signing, body integrity, replay protection, tool integrity, and audit trail.

Background check for AI agents — discover, assess, and test before you ship

The security layer for AI agents — platform-agnostic threat detection with 300+ rules, runtime blocking, and remediation guidance. Continuous protection.

Deterministic execution-time authorization engine for AI agents. Evaluates proposed actions against intent, state, and policy before execution and emits cryptographically verifiable authorization artifacts.

Security middleware for MCP servers. Trust-based access control, rate limiting, and audit logging. Zero dependencies.

Runtime governance, PII redaction, and audit logging for OpenClaw agents

Lightweight security guardrails for tool-enabled agent runtimes: scan risky payloads, redact secrets, expose stdio/HTTP MCP tools, and write audit logs.

Runtime security layer for AI agents. Enforces policy on tool calls to block prompt injection and unsafe actions.

Playwright reference adapter for the SafeBrowse runtime

The credit check for AI agents. Trust scoring, signed payments, spend limits, and compliance for autonomous agents.

Local-first OpenClaw trust plugin for prompt-injection risk scoring, skill scanning, transcript hygiene, and posture reporting in minutes.

CLI tool to manage OpenTrust AI Agent Runtime Security Platform — setup, start, stop, status, logs

Core SafeBrowse policy runtime for browser-use agents

Safety for Agents — ADR layer for OpenClaw

Independent runtime audit and alerting for OpenClaw-like local agents.

Cybersecify -- Security agent for AI developers. Audit OpenAPI x-agent-trust compliance, scan MCP servers, check packages, audit dependencies, verify repos, check agent threats. Works in Cursor, Claude Desktop, any MCP client. Supports the officially regi

Ron Enterprise Core — 32-layer multi-tenant agentic engine

Cryptographically signed delegation receipts for AI agents. Define exactly what an AI can and can't do — signed, verifiable, tamper-proof.

AI Agent Security — scan every tool call for secrets, PII, destructive commands, and prompt injection. Runs locally, zero dependencies, no signup required.

Security scanner for AI agent packages — CLI + MCP server

MCP server that gives AI agents 12 security tools powered by a multi-stage detection pipeline. Scans prompts, responses, SQL, file writes, and web searches for injection attacks, PII leaks, and policy violations. Session correlation engine with human-in-t

Open-source AI prompt injection and data exfiltration detector. Drop-in security for LLM agents.

OpenClaw plugin for prompt injection detection. Drop-in security scanning that hooks into message, tool call, and tool result lifecycle events using heuristic pattern matching. For the full SDK with ML classification, custom rules, and audit logging, see

Localhost SafeBrowse daemon for browser-use agent enforcement

MCP server for Vigile AI Security — query trust scores for MCP servers and agent skills from within Claude Code, Cursor, and other AI agents

Runtime security for AI Agent Skills — Scan, sandbox & enforce. Detect prompt injection, memory poisoning, supply chain attacks. 72+ patterns, 14 categories. The firewall Snyk and Cisco don't build.

Static security auditor for AI agent configs — CLAUDE.md, .mcp.json, .cursorrules. Compound threat detection, OWASP mapping, SARIF output.

Algiz security plugin for OpenClaw - detect and defend against agent threats: secret masking, command guard, prompt injection scanner

Cryptographic security layer for AI agents. Verify instruction origin before execution.

OpenTrust Core — AI Agent security engine with content detection and behavior assessment

AARI Execution Firewall plugin for OpenClaw — intercepts tool calls before execution and enforces ALLOW/WARN/BLOCK decisions

The only thing that makes AI agents production-ready. Cryptographic identity, boundary enforcement, and kill switch for autonomous agents.

Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix. For Claude Code, Cursor, Windsurf, Cline, OpenClaw.

The security gateway for AI agent communication protocols (MCP, A2A). Prompt injection detection, audit logging, rate limiting, trust scoring, and policy enforcement.

LangChain.js security integration for Weave Protocol - callbacks, tool wrappers, and retriever guards

Multi-tenant AI agent runtime with OS-level isolation. Sandboxed execution, encrypted credentials, private memory per tenant — one server, no Docker.

Thin OpenAI Agents SDK adapter for the OxDeAI universal execution guard

Thin LangGraph adapter for the OxDeAI universal execution guard

the credit score for context — security scanning for packages, repos, MCP servers, skills, domains and commits

Universal execution authorization guard (PEP boundary) for OxDeAI

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

Security protocol for autonomous AI agents — contract verification, wallet monitoring, freeze protection, and x402 machine payments.

AI agent security: scan skills for 25 attack classes + runtime monitoring (EDR for AI agents). Real-time scanning, behavioral anomaly detection, session monitoring, exfiltration alerts. 1,316+ findings from 450+ audits. OWASP Agentic AI Top 10 mapped.

MCPS security node for n8n -- adds cryptographic signing, tool pinning, replay protection, and audit trails to MCP workflows

SpiderRating MCP Server — security scanning and trust scores for MCP servers and agent skills

Prompt SecGuard — 在消息和工具数据进入 LLM 前进行安全扫描，检测提示词注入攻击

Infinity Protocol — Cryptographic agent-human trust layer + security hardening. The loop never breaks. ♾️🐝

Security firewall for AI agents — intercept MCP tool calls, enforce policies, block attacks

Security moat for AI agents. Runtime protection against prompt injection, tool misuse, and data exfiltration.

Zero-trust security proxy for MCP servers. Logging, rate limiting, injection detection, and policy enforcement.

Security runtime for AI agents — protect against malicious tools, data theft, and prompt injection

MAP (Model Context Authorization Protocol) — enforcement proxy for MCP servers

Thin AutoGen adapter for the OxDeAI universal execution guard

AI agent security platform — scan, fix, monitor, and pentest MCP servers, Claude skills, Codex plugins, Cursor extensions, and 5 more platforms. 227 rules across 17 threat categories.

Thin OpenClaw adapter for the OxDeAI universal execution guard

Thin CrewAI adapter for the OxDeAI universal execution guard

Compact instruction DSL for AI agent systems — 6-axis encoding with 4,096 instruction states in 6 tokens

Agent runtime security middleware — scans tool inputs/outputs for prompt injection

Optional npm/npx wrapper for SkillGate CLI (Python core runtime)

Free, zero-friction CLI that audits MCP servers for memory poisoning vulnerabilities in <30 seconds. US-based security platform.

Security scanner for AI agent architectures - 220+ detection patterns and 5 runtime guard modules for prompt injection, SSRF, path traversal, credential exposure, MCP security, and OWASP ASI vulnerabilities

Package gateway for AI agents - secure package installation with CVE scanning and threat detection

Enterprise-grade MCP firewall for conscious AI stewardship - Zero-trust security layer for Model Context Protocol servers

OCC provenance plugin for OpenClaw — cryptographic proof of every agent action.

Lightweight, zero-Python security scanner MCP server for AI coding agents. Fast install (~5s), 1700+ vulnerability rules with pure JavaScript regex engine, 4.3M+ package hallucination detection. For Claude Code, Cursor, Windsurf, Cline.

SafeKeyLab Enterprise MCP Server - Agent Security, RAG Protection, and Compliance

AI got hands. This is the leash. Policy, audit, kill switch for any AI agent with access to your accounts.

Security plugin for Clawdbot. Enforces human intent boundaries inside the agent.

Security moat for AI agents. Runtime protection against prompt injection, tool misuse, and data exfiltration.

OpenClaw plugin that validates agent inputs, tool calls, and messages through the Membrane AI guard API

TypeScript client for the AumOS OWASP ASI Top 10 defensive library — agent security scanning, threat detection, and compliance reporting

Security scanner for AI agent skills and prompts - detects prompt injection, jailbreaks, and data exfiltration

OpenClaw plugin for CAUL security membrane — evaluates every tool call through 4 security rings

agent-secrets-guard-server: zero-trust credential broker for AI agents

Official SecureClaw package has moved to @adversa/secureclaw — AI agent security hardening for OpenClaw by Adversa AI

Security layer for AI agents - blocks prompt injection, credential exfiltration, and malicious commands

Sentinely — Security layer for AI agents. Stop prompt injection, memory poisoning, and agent drift in 3 lines of code.

Evaluate AI agent plans before they execute. Returns ACCEPTED, RESTRICTED, or BLOCKED. Powered by Vouch.

Governance guard for Claude Managed Agents. Evaluates every tool call before execution. ACCEPTED flows. RESTRICTED steers. BLOCKED stops.

SupraWall credential vault and security layer for Paperclip AI companies. Every agent gets only the credentials it's authorized to use, for only as long as it needs them.

MosheSDK shared types, schemas, and validators

MosheSDK Anthropic tool-use adapter — no anthropic SDK dependency required

MosheSDK file-backed session, artifact, and approval store

Drop-in behavioral telemetry for AI agents. 3-line integration, local SQLite storage, framework-agnostic.

Spectral ruleset for OpenAPI x-agent-trust compliance. Validates agent authentication security schemes per the OpenAPI Extensions Registry.

MosheSDK in-memory session, artifact, and approval store

MosheSDK OpenAI tool-call adapter — no openai SDK dependency required

Lighthouse for AI agents. Security scanner, PII protection, prompt defense audit.

MosheSDK core engine — 7-stage pipeline, policy, analyzers, taint, chain risk

TypeScript SDK for MosheSDK — runtime security for AI agents

MosheSDK generic tool adapter — wrap any tool call through the safety pipeline

VerifiedX TypeScript SDK

AgentLair integration for Mastra — agent identity verification, behavioral trust scoring, and trust-gated tool execution.