freshcrate — #agent-security

Home > #agent-security

Tag: #agent-security

6 packages • ⭐ 3,824 total stars

AI-Infra-Guardv4.1.4🌿 Growing⭐3,428

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.

agent agent-security ai-infra ai-red-teaming ai-security llm llm-evaluation llm-jailbreak pythonby Tencent

medusav2026.5.5🌿 Growing⭐252

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

agent-security ai-security code-analysis cve-detection devsecops llm-security mcp nextjs pythonby Pantheon-Security

secure-claude-codev15.0.0🌿 Growing⭐100

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.

agent-security ai-security claude claude-code claude-cowork devsecops exfiltration-detection git-security mcp pythonby efij

AgentWardmain@2026-04-20🌱 Seedling⭐30

AgentWard – Built for all, hardened for OpenClaw.

agent-security defense-in-depth llm-agent llm-security openclaw openclaw-plugin openclaw-security prompt-injection-defense typescriptby FIND-Lab

opena2av0.8.23🌱 Seedling⭐13

Open-source security tools for AI agents. Find vulnerabilities, fix root causes, prove compliance.

agent-security ai-agents ai-security claude-code compliance copilot credential-protection cursor mcp typescriptby opena2a-org

acr-frameworkv1.1.0🌱 Seedling⭐1

ACR Control Plane: runtime control & governance for agentic AI (six-pillar enforcement).

agent-security agentic-ai ai-control-plane ai-framework ai-governance ai-governance-framework ai-runtime-governance ai-runtime-security pythonby AdamDiStefanoAI