We5ter/Scanners-Box
The Ultimate Open-Source Security Arsenal for Hackers, Enterprises, and AI Agents——面向极客、企业与 AI 智能体的全域开源网络安全工具矩阵
Topic: agent-security-tools
17 repositories
hackwither/reap
reconnaissance for agent attack surfaces
votal-ai-hq/ai-red-teaming
Whitebox & Blackbox AI red-teaming framework for LLMs & Agentic AI apps. It analyzes your app's source code to discover tools, roles, and guardrails, then generates new attacks chains across several categories and adapts over multiple multi turn rounds to find vulnerabilities
putervision/WebCrypt
Zero-dependency Web Crypto suite & Model Context Protocol (MCP) server for AES-256-GCM, RSA-4096, and AI agent security.
splyntra/splyntra
splyntra
stashbase/cli
Open-source access layer for coding agents. Scoped secrets, APIs, tools, files, and dependencies for Claude Code, Codex, Cursor, and more.
YashvantHange/AgentArmor
🛡️ Open-source AI security scanner & LLM red-teaming platform. Test LLM APIs, chatbots, agents, MCP servers & RAG for prompt injection, jailbreaks, data leaks & unsafe tool use — with OWASP LLM Top 10 mapping and plain-English, audit-ready reports.
xinbetween/learn-agent-security-from-scratch
A free course on AI agent security: prompt injection, tool poisoning, memory attacks, MCP supply chain, CaMeL, information-flow control, sandboxing and red-teaming. 27 chapters, runnable Python, interactive labs, six projects.
freshxiaoyao/openclaw-human-gate
Manual Verification Protection + AI Selector Compatible with OpenClaw . This is a complete TypeScript plugin project—a true implementation of the `before_tool_call` hook that can intercept tool calls, follow OpenClaw’s built-in approval workflow, and features an approval window mechanism.
thepeternemec/TailorLayer
Evidence-first security review for agent repositories: source-linked findings, suggested fixes, drift checks, and least-privilege launch plans.
mlawsonking/MCP
Deterministic guards and web tools for AI agents (MCP + HTTP APIs)
putmanmodel/kingpin-weak-signal-demo
Runtime capability governance for AI agents. Kingpin separates what an agent notices or believes from what it is authorized to do, using scoped leases, human review, retry controls, prompt-injection handling, and deterministic audit behavior.
rootkiller6788/dsh-plugin-scanner
A plugin-native security scanner for DeepSeek Harness that detects capability escalation, config hijacking, prompt injection, dangerous code, and self-modifying behavior.
srimontidutta/AgentRiskBOM
AgentRiskBOM provides a security bill of materials for reviewing the delegated authority of tool-using AI agents.
siju-asari/agent-maestro-scnnaer
Discovers agents — A2A protocol agents via their published Agent Card, or plain OpenAPI/Swagger REST services that don't speak A2A at all — then runs a rule-based threat analysis against each one using the MAESTRO framework (Multi-Agent Environment, Security, Threat, Risk, and Outcome — CSA's 7-layer threat model for agentic AI).
alemarcosa/daedalab
Daedalab is a control layer for AI agents that intercepts tool calls, blocks dangerous actions, enforces spending limits, and keeps a complete audit trail, giving users control over what their agents can do before it happens.
psandhir/horustrace
Open-source static security analysis for agentic systems, with dependency graphs, capability tracing, MCP analysis and attack-path detection.