Search

Autonomous AI red team simulation agent for web application penetration testing. 7 specialized agents, containerized Kali tools, streaming case pipeline, 57 security references. Powered by OpenCode.

Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for the agentic stack.

Static security scanner for AI agents. Catches prompt injection, runaway loops, missing oversight, and compliance gaps across 21 frameworks. Use from Claude Code, Cursor, ChatGPT (MCP), the CLI, or GitHub Actions.

Autonomous AI bug bounty hunter — agentic ReAct loop, dual-brain offensive security LLM via OpenAI-compatible API, 60+ tools, 7-layer FP elimination, HUNTER mode, proof-of-exploit. Works with LM Studio / llama.cpp / Ollama / vLLM.

Agent framework for remediating GitHub security alerts.

Security Trust Report: [email protected] — 54/100 (C, standard). Security incident detected. Maintainer risk, supply chain analysis from 8 security databases.

Security scanner for AI agent tool definitions

GitHub security posture analysis for AI agents — 39 MCP tools, 45 checks across org, repos, Actions, secrets, supply chain, and access control

The dashcam and emergency brake for AI agents. A security proxy that physically blocks rogue LLM commands and generates cryptographically proven audit trails for enterprise compliance.

A safety layer that lets developers use AI coding agents at work without triggering security alerts

Portable, standards-backed security policies for any AI coding agent. One command to install OWASP, CWE, NIST rules + security skills.

OWASP Foundation web repository

The Open Authorization Standard for AI Agents. Framework-agnostic tool permissions, identity verification, scoped access control, and audit logging for any AI agent.

Responsible AI auditing for LLMs and SLMs — deception, fairness, sociotechnical risk, regulatory compliance

Testing tool for AI engineers: quality, optimization, vulnerability, guardrails, and copy-paste fixes for LLM prompts.

Static analyzer and GitHub Action for detecting Agentic Workflow Injection risks in AI-powered GitHub Actions workflows.

The Pydantic-based Firewall for MCP Servers. Stops hallucinated tool calls, validates schemas, and sandboxes dangerous operations.

Discover and inventory autonomous AI agents across your infrastructure - static analysis, runtime detection, and Kubernetes monitoring

Official Python SDK for AgentGuard Intelligence Engine and Action Firewall.

Runtime firewall for AI agents - blocks catastrophic tool calls and self-heals the run.