
MISP
MISP (core software) - Open Source Threat Intelligence and Sharing Platform

MISP (core software) - Open Source Threat Intelligence and Sharing Platform

Sandboxed runtime for autonomous AI agents with declarative YAML policies enforcing filesystem, network, and process constraints, plus endpoint-bound…

Python library for adversarial machine learning security, enabling red and blue teams to run evasion, poisoning, extraction, and inference attacks…

POC for CVE-2026-78006 The Events Calendar <= 6.17.4 - Unauthenticated PHP Object Injection to Remote Code Execution

Static analysis CLI that scans AI-generated code for vulnerabilities like SQL injection, unsafe reflection, and hardcoded secrets, with SARIF export…

Sandbox for AI coding agents. Runs Copilot CLI, Claude Code, OpenCode, Gemini CLI, Antigravity, Pi, goose or a plain shell inside a kernel-level…

Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.

Programmable guardrails for LLM chat apps: enforce input/output rails, block jailbreaks and prompt injections, detect hallucination, and mask…

Desktop monitoring and local security reviews for AI agents, with opt-in policy-controlled execution and MCP action tools. Windows primary;…

Autonomous AI pentesting agents — real-time reconnaissance, vulnerability detection, and exploitation orchestration. Go + TypeScript.

Windows network reconnaissance scanner with ping sweeps, TCP port scanning, and deep AI/ML service detection for finding shadow AI, rogue LLM…

Set of tools to assess and improve LLM security.

Local-first AI red team for web, API, and LLM application security. Attacker-style reasoning, evidence-backed findings, and skills for AI coding…

NVR with realtime local object detection for IP cameras

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt…

A structured knowledge base covering AI security fundamentals, threat modeling, red team offensive techniques, and blue team defenses, including LLM…

Self-hosted threat intelligence platform — feed aggregation, AI triage, MITRE ATT&CK coverage, and Sentinel-integrated detection engineering. Runs…

IFRIT is an AI-powered reverse proxy that intercepts incoming requests in real time, classifying each one as legitimate or malicious. Legitimate…