42 packages found
@enmanuelmagTransparent MCP proxy with OpenTelemetry tracing. Wrap any MCP server and persist traces to SQLite, Postgres or MySQL.
MISP (core software) - Open Source Threat Intelligence and Sharing Platform
PFI: Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
Comprehensive paid advertising audit & optimization skill for Claude Code. 250+ checks across Google, Meta, YouTube, Lin
A full marketing department for Claude Code. Skill packs for Klaviyo, Shopify, GA4, Looker Studio, paid media, and more.
It is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learning Represe
MISP (Malware Information Sharing Platform) MCP server with built-in prompt injection defense via prompt-defense-audit
🛡️ Modern Python code obfuscator - Enterprise-grade protection at 50% lower cost than PyArmor
Eleven Claude Code skills ported to OpenCode: code-review, security-review, feature-dev, frontend-design + 7 more. One c
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development f
A transparent Go proxy that intercepts, signs, and audits all MCP tool calls between any client and server, without modi
A Claude Code skill bundle for bug hunting and external red-team work — 71 skills, 15 slash commands, 681 disclosed-repo
AI-Powered Paid Advertising Audit & Optimization — 190 checks across 5 platforms, AI creative scoring, live API connecto
Enterprise AI bastion host for secure AI API and MCP access, with unified proxying, RBAC, audit logs, rate limiting, and
Security infrastructure your AI can't be — deterministic, daily CVE intel past your model's training cutoff, whole-repo-
Supply chain risk scorer for npm and PyPI — single-maintainer CRITICAL flags before attacks happen
Deterministic refund, cancel, trial, and return policy decisions for support teams. One verdict for humans and AI agents
GUARDRAIL - MCP Security - Gateway for Unified Access, Resource Delegation, and Risk-Attenuating Information Limits
RamiBot v3.8.0 is a local-first AI security operations platform integrating multi-LLM support, a dynamic red/blue team s
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 238 commands, 224 MC
The simplest AI-ready secrets manager. Local-first, single-binary CLI & Desktop app with MCP integration. Never expose s
MCP server for AIR Blackbox. Expose audit, replay, scan, and compliance tools to any MCP-compatible agent or IDE.
MCP Server for Wazuh SIEM
A beautiful, zero-config visual CVE dashboard for npm & Python. One command: npx osv-ui. 100% Local & Secure.
A Claude Skill for scoring B2B website visual quality across 5 conversion-focused dimensions
The Complete AI Development Toolkit for Claude Code — 103 skills, 36 agents, 172 hooks. Production-ready patterns for fu
Recovery Operating System for Ecommerce/D2C. Ten Claude Code skills for Core-Update recovery, AI search visibility, deci
Claude Skill that audits your projects for RLS misconfigurations, exposed keys, auth bypasses, and storage vulnerabiliti
AI text humanizer for prose, code & academic writing. 100+ patterns, two-pass audit, three-tier scoring, voice injection
CMMC 2.0 compliance advisor as a Claude Code skill. All 3 levels, 14 domains, 110 practices; CUI scoping, SSP + POA&M; m
Audit your Claude CLI history. Visualize, browse, edit -- all with one command, all local, no auth
Claude Skills for Governance, Risk, & Compliance (GRC): Expert-level compliance guidance for ISO 27001, SOC 2, FedRAMP,
Official companion repository for our survey "A Survey of the OpenClaw Ecosystem: From Platform Extensibility to Constra
An AI red-team agent for authorized labs and web app pentesting workflows. Turns Claude Code / OpenCode / Codex into a s
The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai
AI agent firewall that intercepts tool calls (file, shell, network) and enforces deterministic policies at sub-microseco
GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deplo
claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a stru
Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automated manusc
🛡️The governance runtime for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit
Passive recon tool. Zero credentials required. Finds Microsoft 365 & Google Workspace tenants, scores email security, fi