25 packages found
A curated list of tools, papers, and datasets for applying AI to cybersecurity tasks. This list primarily focuses on mod
Open, audit-grade agentic data quality framework with portable industry packs
Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enfor
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development f
Secure NotebookLM MCP Server - Query Google NotebookLM from Claude/AI agents with 17 security hardening layers
MCP server with 39 tools for web design analysis — layout extraction, motion detection, quality scoring, accessibility a
MCP server for AI agent governance - quantum-safe audit trails, policy enforcement, threat detection. Works with Claude
AI code security scanner MCP server — detects invisible Unicode, Trojan Source, homoglyphs, Glassworm steganography, rul
Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, re
Claude Skills for Governance, Risk, & Compliance (GRC): Expert-level compliance guidance for ISO 27001, SOC 2, FedRAMP,
AI-first security scanner with 79 analyzers, 40,000+ detection rules, and repo poisoning detection for AI/ML, LLM agents
Build, run and scale AI agents like API and microservices - observable,auditable and identity-aware from day one.
It is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learning Represe
The Complete AI Development Toolkit for Claude Code — 103 skills, 36 agents, 172 hooks. Production-ready patterns for fu
Bug bounty agent framework for Claude Code, Codex, Gemini, Cursor, Windsurf, Copilot, and OpenClaw — 48 agents, 26 comma
Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats aut
Run Claude in self-improving loops to optimize measurable goals.
Collection of role-based AI personas (e.g. senior-frontend-developer, security-engineer, technical-writer) with .claude
Passive recon tool. Zero credentials required. Finds Microsoft 365 & Google Workspace tenants, scores email security, fi
Inkog MCP Server — the pre-flight check for AI agents
rUvOS — the agentic operating system. A single static Rust binary that runs as an MCP server, giving Claude Code persist
A beautiful, zero-config visual CVE dashboard for npm & Python. One command: npx osv-ui. 100% Local & Secure.
754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3F
AI/ML security — prompt injection defense, model hardening, data poisoning prevention
@semgrep