43 packages found
The trust and intelligence layer between AI agents and your database. Read-only by architecture, semantic knowledge grap
AI Agent Security Middleware — 8-layer defense, DLP data flow, prompt injection detection, zero dependencies. SDK + MCP
Open-source permission control plane for AI agents. Scan, enforce, and audit every tool call.
Zero-Trust PII & secrets sanitizer. Locally scrubs data in-memory before sending context to LLMs.
Claude Skills for Governance, Risk, & Compliance (GRC): Expert-level compliance guidance for ISO 27001, SOC 2, FedRAMP,
LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more fra
Enterprise AI bastion host for secure AI API and MCP access, with unified proxying, RBAC, audit logs, rate limiting, and
MCP server for reading and editing Word (.docx) documents with track changes, comments, footnotes, and structural valida
Governed shared memory for AI agent fleets — multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audi
Secure MCP server for safe, read-only DB access by AI agents, with SQL guardrails, table allowlists, PII masking, and au
🔒 Enterprise-grade API gateway that helps you monitor and impose cost or rate limits per API key. Get fine-grained acce
Governed observability + governance for on-endpoint local LLMs (Ollama): model policy, deterministic prompt scanner, rou
MCP Security Solution for Agentic AI — real-time proxying, behavior analysis, and malicious tool detection
ESLint for your database — CLI + SaaS dashboard
A Claude Code skill bundle for bug hunting and external red-team work — 71 skills, 15 slash commands, 681 disclosed-repo
Claude Code skills suite for AI-driven Odoo 17/18/19 development: read ground truth from the running instance first (fie
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.
Automated security investigation tool using Microsoft MCP Servers, GitHub Copilot, Python Modules and custom copilot-ins
AI gets the context. Not your secrets. Open-source privacy proxy for LLMs.
Security infrastructure your AI can't be — deterministic, daily CVE intel past your model's training cutoff, whole-repo-
Universal preflight security scanner for AI coding agents — Detects hooks injection, credential exfiltration & backdoors
Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety direct
The open agent control plane. Govern autonomous AI agents with pre-execution policy enforcement, approval gates, and aud
A full marketing department for Claude Code. Skill packs for Klaviyo, Shopify, GA4, Looker Studio, paid media, and more.
Find vulnerabilities. Ship secure. — Senior security-engineer skill for AI coding agents. OWASP Top 10, CWE Top 25, secr
A collection of Claude Code and OpenAI Codex Agent Skills for mobile application security testing
@anthropics✓ OfficialAn AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities.
Claude Code security skills: /security-review, /full-scan, /security-scan — with test harness and fixtures
A security scanner for your LLM agentic workflows
OSINT knowledge base + MCP server for autonomous AI agents — Claude Code, Cursor, Kimi K3, recon & threat intel playbook
Generate, validate, parse and audit ISO 20022 pacs.008 (FI-to-FI Customer Credit Transfer) messages with scheme-aware ru
MCP server for AI agent governance - quantum-safe audit trails, policy enforcement, threat detection. Works with Claude
Production-grade Playwright + TypeScript QA framework with AI-powered testing, LLM-as-Judge evaluation, MCP server, 7 CL
A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/Apps Script
A transparent Go proxy that intercepts, signs, and audits all MCP tool calls between any client and server, without modi
GUARDRAIL - MCP Security - Gateway for Unified Access, Resource Delegation, and Risk-Attenuating Information Limits
PyRASP is a Runtime Application Self Protection package for Python-based Web Servers (Flask, FastAPI and Django), Server
A production-grade, schema-aware PostgreSQL MCP server for enterprise AI. Features Zero-Trust SQL validation, multi-tier
Standalone MCP server — cross-session memory, 10-gate VERITAS build pipeline, cryptographic audit ledger, Cortex approva
Opinionated claude.md template for Claude Code that enforces software engineering best practices: security, tenant isola
@semgrep