Tag: #agent-security
8 packages âĸ â 3,863 total stars
A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
AI-first security scanner with 76 analyzers, 9,600+ detection rules, and repo poisoning detection for AI/ML, LLM agents, and MCP servers. Scan any GitHub repo with: medusa scan --git user/repo
AgentWard â Built for all, hardened for OpenClaw.
AI Agent Governance for TypeScript â policy enforcement, scoring, compliance, and audit for AI agents
Open-source security tools for AI agents. Find vulnerabilities, fix root causes, prove compliance.
Security guardrails for Claude Code, MCP tools, and Claude cowork workflows. Local-first modular YARA-style guard packs for secrets, exfiltration, prompt injection, MCP abuse, and risky agent actions.
Security scanner for AI agent tooling â MCP servers, tool definitions, and agentic pipelines
ACR Control Plane: runtime control & governance for agentic AI (six-pillar enforcement).