🛡️ We handed 20 open models a shell. 20 of them ran a dangerous command.
ViKernel Scanner is a free AI model security scanner. It hands a model 8 mock tools (files, mail, web, shell, payments), sends 100 attack checks plus 20 normal-work controls, and records every tool call the model tries to make. It scores what a model does, not what it says.
Reference scans of 20 widely used open-weight models through the Hugging Face router: • 20 of 20 graded F • The median model attempted a dangerous action in 40 of 100 checks • Plain and disguised commands (base64, hex, ROT13, reversed text, quote breaks) reached the shell tool
With ViKernel Firewall placed inside the model weights, 897 of 897 dangerous calls were denied before execution. The firewall judges the action, not the words, and because it lives in the weights it cannot be quietly removed.
Any OpenAI-compatible endpoint (Hugging Face router, OpenRouter, OpenAI, Anthropic, Gemini, Together, Groq, your own vLLM). About a minute per model, graded A to F. Open source, clone it, run it locally.
🛡️ AI Model Hacking Hackathon is LIVE · USD 4,500 in prizes
AI agents now read mail, open files, browse the web and run shell commands. A single crafted email was enough for EchoLeak (CVE-2025-32711), and a coding agent wiped a production database during a code freeze. The risk has moved from what models say to what agents do.
ViKernel is a security kernel that sits at the tool-call boundary, like an OS kernel at the system-call boundary. Every tool call gets ALLOW or DENY before it runs, and every verdict goes into a hash-chained audit trail.
Now we want you to break it. 🔓
🎯 Season 1 · Agent Hijack (Beginner) 🕵️ Season 2 · Data Exfiltration (Intermediate) ✉️ Season 3 · Hidden Instruction (Advanced): plant a mail, a document or a page and make the agent act on it 💥 Season 4 · Kernel Breach (Expert)
Every season has two prizes: Top score (USD 500, and USD 1,000 in Season 4) and a USD 500 Special Award for the most outstanding finding.
Seasons 1, 2 and 3 are open now until Jan 16. Season 4 opens right after.
Day 1: 6 players, 56 submissions, 14 accepted breaches, and 11 causes fixed in the kernel the same day.
✅ Hugging Face sign-in + a browser. No coding, no GPU. ✅ Mock tools, so attack freely. ✅ Prompt guide with copy-ready attacks for every season. ✅ Live leaderboard and a measured baseline to beat.
Safe AI is built by everyone who tries to break it. Bring your strangest idea. 🤗
🌦️ Which weather model is most accurate? We score them every day, in the open.
We released two things on Hugging Face:
🏆 Global Weather Model Leaderboard Every day it records what each global model predicted for 24 world cities, compares it with what actually happened (ERA5), and updates the ranking. ECMWF IFS and AIFS, NOAA GFS and AIGFS, DWD ICON, JMA, ECCC GEM, MET Norway, side by side, on the same cases, since 1 January 2026.
Four elements, four tabs: max temperature, min temperature, wind, precipitation. Forecast leads from 1 to 7 days, with 8 to 10 days joining as they are verified.
🧬 Darwin-Prediction-Weather VIDRAFT's weather prediction system: a fusion engine that combines global forecasts, learning only from days already observed. It holds the lowest error in all four elements at every lead on the 2026 record, and the lowest error in all 15 evaluated cells of the WeatherBench 2 (2020) protocol.
What the 2026 record shows so far: • AI models now lead physics models at the major centres (AIFS vs IFS, AIGFS vs GFS) • Fusion goes further: 7-day max temperature RMSE 2.09 °C vs 2.41 °C for the next model
Also inside: yesterday's results with a daily WIN for the closest model, a 10-day outlook for every city, champions by city and by month, and a Live Earth map with wind, clouds, radar and temperature.
Every forecast and every observed value is open as CSV, so anyone can check the scores.