seawolf's picture

seawolf PRO

seawolf2357

AI & ML interests

None yet

Recent Activity

reacted to SeaWolf-AI's post with šŸ”„ about 3 hours ago
šŸ›”ļø 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. 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 about 6 hours ago
FINAL-Bench/ViKernel-Scanner
reacted to SeaWolf-AI's post with šŸ‘ 1 day ago
šŸ›”ļø AI Model Hacking Hackathon is LIVE Ā· 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. šŸ”“ šŸŽÆ Season 1 Ā· Agent Hijack (Beginner) šŸ•µļø Season 2 Ā· Data Exfiltration (Intermediate) āœ‰ļø Season 3 Ā· Hidden Instruction (Advanced): plant a mail, a document or a page and make the agent act on it šŸ’„ Season 4 Ā· 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. āœ… Hugging Face sign-in + a browser. No coding, no GPU. āœ… Mock tools, so attack freely. āœ… Prompt guide with copy-ready attacks for every season. āœ… Live leaderboard and a measured baseline to beat. Safe AI is built by everyone who tries to break it. Bring your strangest idea. šŸ¤— šŸ•¹ļø Start hacking: https://huggingface.co/spaces/FINAL-Bench/ViKernel-RedTeam šŸ“– Read the full story: https://huggingface.co/blog/FINAL-Bench/ai-model-hacking-hackathon-safe-ai-is-built-by-eve #AISafety #RedTeaming #AIAgents #PromptInjection #Hackathon
View all activity

Organizations

KAISAR's profile picture VIDraft's profile picture korea forestry's profile picture PowergenAI's profile picture OpenFree_AI's profile picture