Coding & Assistance shortlist

AI Security

Security testing, guardrails, and compliance-grade operation controls

Tool List

20 tools

Playground

AI-agent security challenge platform where players break public agent challenges for weekly rewards

Constellation Gate AI

AI agent gateway for prompt-injection defense, secret scanning, auditability, and token compression

Astra

Astra helps teams build AI agents with strict privacy controls so sensitive data stays protected

Astra Security

AI-assisted security scanning and penetration testing platform for websites, applications, and compliance workflows

CyberStrikeAI

AI-native security testing platform with multi-tool orchestration

WinClaw

A security-first desktop AI agent platform for high-compliance environments

DCP

Security layer for encrypted permissions, keys, and access control for AI agents

BestDefense.io

Continuous security validation platform that pentests every deploy, validates exploitable vulnerabilities, and generates remediation PRs

Cynative Security Research Agent

Read-only, fail-closed security research agent for code and cloud infrastructure

Rivault

Privacy vault for securely supplying personal data and context to AI agents

Halo by Scam AI

On-device Windows safety tool that flags suspected synthetic faces and face swaps during live video calls

hotcell

Run local AI-agent sandboxes on your own Mac, Linux host, or server

AboutSecurity

Everything for pentest. | 渗透测试知识库，以 AI Agent 可执行的格式沉淀安全方法论

everything-claude-code

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond

agentshield

AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️

promptfoo

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic

pentest-ai

Offensive-security MCP server with 205 wrapped tools, 17 specialist agents, and 60 SPA-aware probes for OWASP Top 10. CLI + MCP, BYO LLM. No API key needed on MCP path

ironclaw

IronClaw is an Agent OS focused on privacy, security and extensibility

PyRIT

The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems

Aegisora

Fine-grained security controls for AI agent tool and API calls