Type a name, or just describe what you need. Results blend keyword and meaning-based search. 30 matches, each with an EU availability status.
Library
Open-source library of 800+ cybersecurity skills for AI coding agents, mapped to MITRE ATT&CK, NIST CSF and other frameworks.
Model · OpenAI
OpenAI cybersecurity model for finding and validating exploitable vulnerabilities, with access limited to vetted defenders.
Model · Google DeepMind
Variant of Google DeepMind's Gemini Flash model family reportedly tuned for cybersecurity tasks.
Agent · OpenAI
OpenAI's cybersecurity program offering vetted access to AI models and Codex Security for vulnerability defense and red teaming.
Model · Cisco
Cisco Foundation AI's open-weight 8B cybersecurity language model built on Llama-3.1-8B, for local deployment.
Model · Aikido
Open-weight cybersecurity model from Aikido, fine-tuned from GLM 5.3 and compressed to 328 GB.
App · Zoom
Zoom feature that analyzes video and audio in real time to flag possible deepfake participants, with a confidence indicator.
Research · OpenAI
AI-assisted discovery of two critical, roughly 20-year-old PHP remote code execution flaws, dubbed PHP2Shell.
App · Google
Android feature that uses Circle to Search and AI to flag scam warning signs in text messages.
App · OpenAI
OpenAI confidential-computing option for running OpenAI models without OpenAI accessing or training on user content.
OpenAI cloud-based security agent that scans code for vulnerabilities and reports findings.
Research · Hacktron
Security research report on an AI-assisted attack chain against OpenAI systems using a libheif bug and an SSO flaw.
Model · Z.ai
Z.ai's open-weights 753B MoE language model, a post-trained GLM-5.2 aimed at coding, agentic tasks and cybersecurity.
Library · Hex-Rays
Official Hex-Rays MCP server that lets AI agents drive IDA for decompiling and analysing binaries.
App · Z.ai
Free Hugging Face Space from Z.ai that runs GLM-powered vulnerability scans on submitted open-source GitHub repositories.
Research · NVIDIA
NVIDIA-announced alliance of companies collaborating on security for open-source AI.
Google account feature that lets users sign in by scanning their face with the device camera, similar to phone face unlock.
Library · NVIDIA
NVIDIA's open-source security scanner for AI agent skills, checking repos, URLs, zips and files for vulnerabilities.
MIT-licensed MCP server and CLI that lets AI agents reverse engineer native binaries, Electron/JS apps, .NET assemblies and websites.
Model · Anthropic
Anthropic's unrestricted variant of the Fable 5.2 model, available to vetted cybersecurity and biomedical organizations.
Agent · Google
Google DeepMind AI agent that finds software vulnerabilities and generates, tests and verifies security patches.
Open-source MCP server exposing 200+ Ghidra reverse-engineering tools to AI agents, as a GUI plugin or headless server.
Open-source tool that reverses Unity IL2CPP builds back into managed .NET DLLs and metadata dumps.
Open-source, cross-platform .NET assembly browser and decompiler that converts compiled .NET code back to C#.
