GitHub

Hardcoded API keys, access tokens and other credentials used by AI coding tools have been found in publicly accessible MCP configuration files on GitHub, according to research …

DeepZero is an open-source engine that automates the search for exploitable Windows kernel drivers. You point it at a folder of binaries and it parses them, pulls them apart, …

Permify is an open-source authorization service that answers access questions at run time: can user X view document Y, which posts can members of team Y edit. It keeps those …

Tencent’s Zhuque Lab built AI-Infra-Guard, an open-source security scanner for AI systems. It fingerprints running services such as Ollama, vLLM and ComfyUI and checks …

ToolHive is an open-source platform that runs Model Context Protocol servers inside containers. An MCP server is the connector that lets an AI client like Cursor or Claude …

The advice is to consume shared threat intelligence. Join the ISAC. Wire the community feeds into your pipeline. This looks like a fine advice and I agree to it. What nobody …

Sift is a free, open-source command line tool that searches for passwords, API keys, and other sensitive data across the places a company keeps its work: local disks, Windows …

A malicious GitHub repository impersonating Anthropic and claiming to offer free access to “Claude Opus 5” is delivering RevStealer, Windows information-stealing malware that …

Failed SSH logins pile up in an auth log, and a scanner walks a website looking for exposed admin paths. CrowdSec reads log sources and HTTP requests, works out which …

Brian Kuan wrote halo-record, a small Python package that sits inside an AI agent and writes down the moves it makes: tool calls, model calls, data access, approvals. Each …

Hazmat is an open-source tool that runs AI coding agents inside a separate account on your own machine. It wraps the harnesses people use: Claude Code, Codex, OpenCode, Cursor …

PentestGPT is an open-source penetration testing agent that points a large language model at a target and lets it work. In its default mode it runs recon, then exploit, then …