Search

AI security testing engine for surfacing prompt leaks, bypasses, and unsafe agent behavior.

vigolium-audit — autonomous agent that performs thorough security audits on your codebase, part of Vigolium

An AI-powered cybersecurity agent that turns natural language into real security tool execution.

ZTAgent: Zero Trust Security for AI Agents. Never trust an agent action. Verify before execution.

A 7-layer scaffold for production AI agent system prompts. Security-first, multi-tenant by design.

Secure email proxy for AI agents — content filtering, PII redaction, and prompt injection detection over MCP

Secure Agent Control Plane & Passport Vault — identity-aware reverse proxy for AI agent credentials.

🛡️ Zero-Trust Security Firewall & AST Sandbox for Autonomous AI Agents & Model Context Protocol (MCP) Middleware

A secure, highly capable MCP server written in Rust. It exposes a comprehensive suite of filesystem operations as tools for AI agents.

Evil Hermes — sovereign agent framework by Lord Tanzeel Shujah Khan. Cyber-security tooling, automation, and adversarial research.

SECURITY RESEARCH PLACEHOLDER — benign, does nothing. Coordinated vulnerability disclosure (dependency-confusion verification) via HackerOne. Not the real package.

NeuroAgentTest (NAT) — AI-powered API testing with multi-agent neural networks, OWASP security scanning, and adaptive test allocation

Hands-on workshop to explore Gravitee’s AI Management Platform: expose, secure, and govern AI Agents, LLMs and MCP servers

🔍 Automate penetration testing with an intelligent agent that organizes security assessments, leveraging local LLMs and Kali Linux for effective exploitation.

Reverse engineered Debian-based live desktop with an AI assistant, browser-accessible workstation, and security, forensics, and reverse-engineering tools.

Secure local AI agent runtime — vault-backed secrets, sandboxed execution, cryptographic audit chain, procedural skill system

Adversarial RL security testing for LLM applications. An attacker agent learns to break chatbots while a defender patches the system prompt in real time.

A security-first agent platform — Models Propose, Records Decide. 17 deterministic constraints gate every LLM proposal before it becomes state.

Autonomous security assessment agent built on MCP — explicit planning, parallel tool calls, tiered memory, MITRE ATT&CK mapping.

OpenTelemetry + Wireshark + Cloudflare for AI Agents. Monitor, inspect, secure, replay, and optimize all traffic between Users, AI Agents, LLMs, and MCP Servers.