Search

Build your own security agents. Open-source framework for agents with live, read-only access to your infrastructure, with no path to widen it. Reasons across AWS, GCP, Azure, Kubernetes, GitHub and GitLab as one system.

Local deterministic security scanner for AI-agent tools, permissions, and traces.

Minimal Clawdstrike tool wrappers for LangChain tools

Minimal Clawdstrike tool wrappers for the Vercel AI SDK

AI-augmented, evidence-first security auditor for authorized testing of web, API, application, container, cloud and LLM/AI-system targets.

🛡️ Security scanner for AI agents, MCP servers & plugins — 30 rules, AST taint tracking, cross-file analysis, kill chain detection. Free & open source alternative to Snyk Agent Scan.

Universal security-audit plugin and CLI engine for AI agents with OWASP-mapped reports.

The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.

Static security analyzer for AI agents — prompt injection, tool input validation, MCP config auditing, secret detection. 53 rules mapped to OWASP Agentic Top 10.

AI-Powered Code Security Analyzer. Pluto is a powerful CLI tool that uses AI to detect security vulnerabilities in your code.

SkillSpector: Security scanner for AI agent skills (Claude Code, Cursor, and similar). Scans skills for vulnerabilities, malicious patterns, and security risks before installation. Supports Git repos, URLs, zips, and local directories; runs static pattern checks and optional LLM semantic analysis; outputs terminal, JSON, and Markdown reports with risk scoring.

OpenAI SDK instrumentation for Adrian security monitoring.

Sound static analysis and LLM reasoning, in one security agent

Core SDK for Adrian multi-agent security monitoring in Node.js.

AI-powered offensive security agent. Autonomous pentesting with 13+ specialized agents, 120+ OWASP test cases, 15+ LLM providers, and Bolt remote tool servers. Your AI red team.

AI Native Agent Skill 安全审计工具 —— LLM 驱动的多阶段代码审计与漏洞复审流水线

Security testing for agentic AI

Discover, assess, and secure AI agents across your infrastructure

Multi-language security scanner for AI agent skills - detects malware, supply chain attacks, and malicious code patterns

AgenticAnomaly is an indirect prompt injection CTF for testing how agentic security operations center (SOC) workflows can be exploited through indirect prompt injection.