Open-source AI security scanner for Codex, Claude Code, and ACP-compatible coding agents—kept current with OpenAI Codex Security.

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.

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.

Build Secure and Compliant AI agents and MCP Servers. YC W23

Security Scanner for Agent Skills

A security scanner for your LLM agentic workflows

Vetix — Automated scanning, identification, and assessment of SKILL security risks.

Static Code Analysis for security teams with Inter file taint analysis. Built for finding vulnerabilities, advanced structural search, derive insights and supports MCP

Security testing that runs inside the coding agent you already use. Source-available, not open source.

Tamper-evident integrity monitor for the MCP config & server files your local AI agents load.

Authorized security testing workspace. v2 TypeScript terminal product on release; v1 Python on pypi-release; Go branch is demo only.

The security-first skill manager for AI agents — every install runs a security scan. Manage skills & MCP servers across 87 agents. Zero-dependency CLI.

AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 19 tools. Works with Claude, GPT-4, or local models. For authorized security research only.

Catch dangerous AI agent skills before they catch you. Zero-dependency security scanner for Agent Skills, SKILL.md and MCP configs.

Cross-Code Organizer (formerly Claude Code Organizer): cross-harness config dashboard for Claude Code, Codex CLI, MCP servers, skills, memories, agents, sessions, security scanning, context budget, and backups.

Customer-run client for Secure MCP Tunnel: connect private or localhost MCP servers to ChatGPT, Codex, the Responses API, and AgentKit without exposing them to the public internet.

Open-source adversary emulation for AI agents and MCP servers.

Reticle intercepts, visualizes, and profiles JSON-RPC traffic between your LLM and MCP servers in real-time, with zero latency overhead. Stop debugging blind. Start seeing everything.

Local-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cursor and more. Token usage, cost, traces and security audit, exported anywhere.

High-performance Google Drive CLI and Model Context Protocol (MCP) Server for LLM/AI agents. Natively execute Google Apps Script (GAS) under a secure whitelisted runtime sandbox, automate transfers, and manage Drive infrastructure.

Run AI coding agents in hardened container sandboxes.

Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

Instant SECURE Full Stack Apps and AI Agents