99
cutechicken
AI & ML interests
None yet
Recent Activity
liked a Space about 7 hours ago
FINAL-Bench/ViKernel-Scanner reacted to SeaWolf-AI's post with ๐ about 7 hours ago
๐ก๏ธ 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:
โข 20 of 20 graded F
โข The median model attempted a dangerous action in 40 of 100 checks
โข 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.
Read the full results: https://huggingface.co/blog/FINAL-Bench/we-handed-20-open-models-a-shell-20-of-them-failed
Scan your model: https://huggingface.co/spaces/FINAL-Bench/ViKernel-Scanner
Source (Apache-2.0): https://github.com/final-bench/vikernel-scanner
Use the scanner on your own models, or on models you are allowed to test.
#AISecurity #LLMSecurity #AIAgents #RedTeaming #PromptInjection liked a Space 1 day ago
FINAL-Bench/ViKernel-RedTeam